added git lfs

.gitignore

@@ -0,0 +1,4 @@
+**/__pycache__/
+.DS_Store
+.idea/
+*.pyc

app.py

@@ -0,0 +1,98 @@
+import gradio as gr
+import torch
+import numpy as np
+
+from yolov5.models.common import DetectMultiBackend
+from yolov5.utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
+from yolov5.utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
+                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
+from yolov5.utils.plots import Annotator, colors, save_one_box
+from yolov5.utils.torch_utils import select_device, time_sync
+from yolov5.utils.augmentations import letterbox
+
+device = 'cpu'
+half = False
+weights = 'yolov5/best_yolov5l6_joint_pseudo.pt'
+model = DetectMultiBackend(weights, device=device, dnn=False, data=None)
+stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
+bs = 1
+imgsz = (640, 640)
+conf_thres = 0.1
+iou_thres = 0.1
+hide_labels = False
+hide_conf = True
+line_thickness = 1
+
+def joint_detection(img0):
+    global imgsz
+    img = letterbox(img0, 640, stride=stride, auto=pt)[0]
+    img = img.transpose((2, 0, 1))[::-1]  # HWC to CHW, BGR to RGB
+    img = np.ascontiguousarray(img)
+
+    im = torch.from_numpy(img).to(device)
+    im = im.half() if half else im.float()  # uint8 to fp16/32
+    im /= 255  # 0 - 255 to 0.0 - 1.0
+    if len(im.shape) == 3:
+        im = im[None]  # expand for batch dim
+    # Padded resize
+
+    # Convert
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Inference
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)  # warmup
+    pred = model(im, augment=False, visualize=False)
+    t3 = time_sync()
+
+    # NMS
+    pred = non_max_suppression(pred, conf_thres, iou_thres, None, False, max_det=1000)
+
+    # Second-stage classifier (optional)
+    # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+    # Process predictions
+    for i, det in enumerate(pred):  # per image
+        im0 = img0.copy()
+        gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+        annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+        imc = im0
+        if len(det):
+            # Rescale boxes from img_size to im0 size
+            det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
+
+            # Write results
+            for *xyxy, conf, cls in reversed(det):
+                c = int(cls)  # integer class
+                label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+                annotator.box_label(xyxy, label, color=colors(c, True))
+
+        # Stream results
+        im0 = annotator.result()
+        return im0
+        # if view_img:
+        #     cv2.imshow(str(p), im0)
+        #     cv2.waitKey(1)  # 1 millisecond
+        #
+        # # Save results (image with detections)
+        # if save_img:
+        #     if dataset.mode == 'image':
+        #         cv2.imwrite(save_path, im0)
+        #     else:  # 'video' or 'stream'
+        #         if vid_path[i] != save_path:  # new video
+        #             vid_path[i] = save_path
+        #             if isinstance(vid_writer[i], cv2.VideoWriter):
+        #                 vid_writer[i].release()  # release previous video writer
+        #             if vid_cap:  # video
+        #                 fps = vid_cap.get(cv2.CAP_PROP_FPS)
+        #                 w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+        #                 h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+        #             else:  # stream
+        #                 fps, w, h = 30, im0.shape[1], im0.shape[0]
+        #             save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+        #             vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+        #         vid_writer[i].write(im0)
+
+    # Print time (inference-only)
+
+iface = gr.Interface(fn=joint_detection, inputs="image", outputs="image")
+iface.launch()

yolov5/detect.py

@@ -0,0 +1,258 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Run inference on images, videos, directories, streams, etc.
+
+Usage - sources:
+    $ python path/to/detect.py --weights yolov5s.pt --source 0              # webcam
+                                                             img.jpg        # image
+                                                             vid.mp4        # video
+                                                             path/          # directory
+                                                             path/*.jpg     # glob
+                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
+
+Usage - formats:
+    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
+                                         yolov5s.torchscript        # TorchScript
+                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                         yolov5s.xml                # OpenVINO
+                                         yolov5s.engine             # TensorRT
+                                         yolov5s.mlmodel            # CoreML (MacOS-only)
+                                         yolov5s_saved_model        # TensorFlow SavedModel
+                                         yolov5s.pb                 # TensorFlow GraphDef
+                                         yolov5s.tflite             # TensorFlow Lite
+                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+"""
+
+import argparse
+import os
+import sys
+from pathlib import Path
+
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import DetectMultiBackend
+from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
+from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
+                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, time_sync
+
+
+
+@torch.no_grad()
+def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
+        source=ROOT / 'data/images',  # file/dir/URL/glob, 0 for webcam
+        data=ROOT / 'data/coco128.yaml',  # dataset.yaml path
+        imgsz=(640, 640),  # inference size (height, width)
+        conf_thres=0.25,  # confidence threshold
+        iou_thres=0.45,  # NMS IOU threshold
+        max_det=1000,  # maximum detections per image
+        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        view_img=False,  # show results
+        save_txt=False,  # save results to *.txt
+        save_conf=False,  # save confidences in --save-txt labels
+        save_crop=False,  # save cropped prediction boxes
+        nosave=False,  # do not save images/videos
+        classes=None,  # filter by class: --class 0, or --class 0 2 3
+        agnostic_nms=False,  # class-agnostic NMS
+        augment=False,  # augmented inference
+        visualize=False,  # visualize features
+        update=False,  # update all models
+        project=ROOT / 'runs/detect',  # save results to project/name
+        name='exp',  # save results to project/name
+        exist_ok=False,  # existing project/name ok, do not increment
+        line_thickness=3,  # bounding box thickness (pixels)
+        hide_labels=False,  # hide labels
+        hide_conf=False,  # hide confidences
+        half=False,  # use FP16 half-precision inference
+        dnn=False,  # use OpenCV DNN for ONNX inference
+        ):
+    source = str(source)
+    save_img = not nosave and not source.endswith('.txt')  # save inference images
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    if is_url and is_file:
+        source = check_file(source)  # download
+
+    # Directories
+    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Load model
+    device = select_device(device)
+    model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
+    stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
+
+    # Half
+    half &= (pt or jit or onnx or engine) and device.type != 'cpu'  # FP16 supported on limited backends with CUDA
+    if pt or jit:
+        model.model.half() if half else model.model.float()
+
+    # Dataloader
+    if webcam:
+        view_img = check_imshow()
+        cudnn.benchmark = True  # set True to speed up constant image size inference
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = len(dataset)  # batch_size
+    else:
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
+        bs = 1  # batch_size
+    vid_path, vid_writer = [None] * bs, [None] * bs
+
+    # Run inference
+    model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half)  # warmup
+    dt, seen = [0.0, 0.0, 0.0], 0
+    for path, im, im0s, vid_cap, s in dataset:
+        t1 = time_sync()
+        im = torch.from_numpy(im).to(device)
+        im = im.half() if half else im.float()  # uint8 to fp16/32
+        im /= 255  # 0 - 255 to 0.0 - 1.0
+        if len(im.shape) == 3:
+            im = im[None]  # expand for batch dim
+        t2 = time_sync()
+        dt[0] += t2 - t1
+
+        # Inference
+        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+        pred = model(im, augment=augment, visualize=visualize)
+        t3 = time_sync()
+        dt[1] += t3 - t2
+
+        # NMS
+        pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+        dt[2] += time_sync() - t3
+
+        # Second-stage classifier (optional)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
+
+        # Process predictions
+        for i, det in enumerate(pred):  # per image
+            seen += 1
+            if webcam:  # batch_size >= 1
+                p, im0, frame = path[i], im0s[i].copy(), dataset.count
+                s += f'{i}: '
+            else:
+                p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
+
+            p = Path(p)  # to Path
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
+            s += '%gx%g ' % im.shape[2:]  # print string
+            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if save_crop else im0  # for save_crop
+            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+            if len(det):
+                # Rescale boxes from img_size to im0 size
+                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
+
+                # Print results
+                for c in det[:, -1].unique():
+                    n = (det[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+
+                # Write results
+                for *xyxy, conf, cls in reversed(det):
+                    if save_txt:  # Write to file
+                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                        with open(txt_path + '.txt', 'a') as f:
+                            f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+                    if save_img or save_crop or view_img:  # Add bbox to image
+                        c = int(cls)  # integer class
+                        label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+                        annotator.box_label(xyxy, label, color=colors(c, True))
+                        if save_crop:
+                            save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+
+            # Stream results
+            im0 = annotator.result()
+            if view_img:
+                cv2.imshow(str(p), im0)
+                cv2.waitKey(1)  # 1 millisecond
+
+            # Save results (image with detections)
+            if save_img:
+                if dataset.mode == 'image':
+                    cv2.imwrite(save_path, im0)
+                else:  # 'video' or 'stream'
+                    if vid_path[i] != save_path:  # new video
+                        vid_path[i] = save_path
+                        if isinstance(vid_writer[i], cv2.VideoWriter):
+                            vid_writer[i].release()  # release previous video writer
+                        if vid_cap:  # video
+                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                        else:  # stream
+                            fps, w, h = 30, im0.shape[1], im0.shape[0]
+                        save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
+                        vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                    vid_writer[i].write(im0)
+
+        # Print time (inference-only)
+        LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
+
+    # Print results
+    t = tuple(x / seen * 1E3 for x in dt)  # speeds per image
+    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t)
+    if save_txt or save_img:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
+    if update:
+        strip_optimizer(weights)  # update model (to fix SourceChangeWarning)
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'best2.pt', help='model path(s)')
+    parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob, 0 for webcam')
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='(optional) dataset.yaml path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='show results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--visualize', action='store_true', help='visualize features')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default=ROOT / 'runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--line-thickness', default=1, type=int, help='bounding box thickness (pixels)')
+    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
+    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
+    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
+    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(FILE.stem, opt)
+    return opt
+
+
+def main(opt):
+    check_requirements(exclude=('tensorboard', 'thop'))
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

yolov5/export.py

@@ -0,0 +1,544 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Export a YOLOv5 PyTorch model to other formats. TensorFlow exports authored by https://github.com/zldrobit
+
+Format                      | `export.py --include`         | Model
+---                         | ---                           | ---
+PyTorch                     | -                             | yolov5s.pt
+TorchScript                 | `torchscript`                 | yolov5s.torchscript
+ONNX                        | `onnx`                        | yolov5s.onnx
+OpenVINO                    | `openvino`                    | yolov5s_openvino_model/
+TensorRT                    | `engine`                      | yolov5s.engine
+CoreML                      | `coreml`                      | yolov5s.mlmodel
+TensorFlow SavedModel       | `saved_model`                 | yolov5s_saved_model/
+TensorFlow GraphDef         | `pb`                          | yolov5s.pb
+TensorFlow Lite             | `tflite`                      | yolov5s.tflite
+TensorFlow Edge TPU         | `edgetpu`                     | yolov5s_edgetpu.tflite
+TensorFlow.js               | `tfjs`                        | yolov5s_web_model/
+
+Requirements:
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime openvino-dev tensorflow-cpu  # CPU
+    $ pip install -r requirements.txt coremltools onnx onnx-simplifier onnxruntime-gpu openvino-dev tensorflow  # GPU
+
+Usage:
+    $ python path/to/export.py --weights yolov5s.pt --include torchscript onnx openvino engine coreml tflite ...
+
+Inference:
+    $ python path/to/detect.py --weights yolov5s.pt                 # PyTorch
+                                         yolov5s.torchscript        # TorchScript
+                                         yolov5s.onnx               # ONNX Runtime or OpenCV DNN with --dnn
+                                         yolov5s.xml                # OpenVINO
+                                         yolov5s.engine             # TensorRT
+                                         yolov5s.mlmodel            # CoreML (MacOS-only)
+                                         yolov5s_saved_model        # TensorFlow SavedModel
+                                         yolov5s.pb                 # TensorFlow GraphDef
+                                         yolov5s.tflite             # TensorFlow Lite
+                                         yolov5s_edgetpu.tflite     # TensorFlow Edge TPU
+
+TensorFlow.js:
+    $ cd .. && git clone https://github.com/zldrobit/tfjs-yolov5-example.git && cd tfjs-yolov5-example
+    $ npm install
+    $ ln -s ../../yolov5/yolov5s_web_model public/yolov5s_web_model
+    $ npm start
+"""
+
+import argparse
+import json
+import os
+import platform
+import subprocess
+import sys
+import time
+import warnings
+from pathlib import Path
+
+import pandas as pd
+import torch
+import torch.nn as nn
+from torch.utils.mobile_optimizer import optimize_for_mobile
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
+
+from models.common import Conv
+from models.experimental import attempt_load
+from models.yolo import Detect
+from utils.activations import SiLU
+from utils.datasets import LoadImages
+from utils.general import (LOGGER, check_dataset, check_img_size, check_requirements, check_version, colorstr,
+                           file_size, print_args, url2file)
+from utils.torch_utils import select_device
+
+
+def export_formats():
+    # YOLOv5 export formats
+    x = [['PyTorch', '-', '.pt'],
+         ['TorchScript', 'torchscript', '.torchscript'],
+         ['ONNX', 'onnx', '.onnx'],
+         ['OpenVINO', 'openvino', '_openvino_model'],
+         ['TensorRT', 'engine', '.engine'],
+         ['CoreML', 'coreml', '.mlmodel'],
+         ['TensorFlow SavedModel', 'saved_model', '_saved_model'],
+         ['TensorFlow GraphDef', 'pb', '.pb'],
+         ['TensorFlow Lite', 'tflite', '.tflite'],
+         ['TensorFlow Edge TPU', 'edgetpu', '_edgetpu.tflite'],
+         ['TensorFlow.js', 'tfjs', '_web_model']]
+    return pd.DataFrame(x, columns=['Format', 'Argument', 'Suffix'])
+
+
+def export_torchscript(model, im, file, optimize, prefix=colorstr('TorchScript:')):
+    # YOLOv5 TorchScript model export
+    try:
+        LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...')
+        f = file.with_suffix('.torchscript')
+
+        ts = torch.jit.trace(model, im, strict=False)
+        d = {"shape": im.shape, "stride": int(max(model.stride)), "names": model.names}
+        extra_files = {'config.txt': json.dumps(d)}  # torch._C.ExtraFilesMap()
+        if optimize:  # https://pytorch.org/tutorials/recipes/mobile_interpreter.html
+            optimize_for_mobile(ts)._save_for_lite_interpreter(str(f), _extra_files=extra_files)
+        else:
+            ts.save(str(f), _extra_files=extra_files)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'{prefix} export failure: {e}')
+
+
+def export_onnx(model, im, file, opset, train, dynamic, simplify, prefix=colorstr('ONNX:')):
+    # YOLOv5 ONNX export
+    try:
+        check_requirements(('onnx',))
+        import onnx
+
+        LOGGER.info(f'\n{prefix} starting export with onnx {onnx.__version__}...')
+        f = file.with_suffix('.onnx')
+
+        torch.onnx.export(model, im, f, verbose=False, opset_version=opset,
+                          training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
+                          do_constant_folding=not train,
+                          input_names=['images'],
+                          output_names=['output'],
+                          dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # shape(1,3,640,640)
+                                        'output': {0: 'batch', 1: 'anchors'}  # shape(1,25200,85)
+                                        } if dynamic else None)
+
+        # Checks
+        model_onnx = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(model_onnx)  # check onnx model
+        # LOGGER.info(onnx.helper.printable_graph(model_onnx.graph))  # print
+
+        # Simplify
+        if simplify:
+            try:
+                check_requirements(('onnx-simplifier',))
+                import onnxsim
+
+                LOGGER.info(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
+                model_onnx, check = onnxsim.simplify(
+                    model_onnx,
+                    dynamic_input_shape=dynamic,
+                    input_shapes={'images': list(im.shape)} if dynamic else None)
+                assert check, 'assert check failed'
+                onnx.save(model_onnx, f)
+            except Exception as e:
+                LOGGER.info(f'{prefix} simplifier failure: {e}')
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'{prefix} export failure: {e}')
+
+
+def export_openvino(model, im, file, prefix=colorstr('OpenVINO:')):
+    # YOLOv5 OpenVINO export
+    try:
+        check_requirements(('openvino-dev',))  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+        import openvino.inference_engine as ie
+
+        LOGGER.info(f'\n{prefix} starting export with openvino {ie.__version__}...')
+        f = str(file).replace('.pt', '_openvino_model' + os.sep)
+
+        cmd = f"mo --input_model {file.with_suffix('.onnx')} --output_dir {f}"
+        subprocess.check_output(cmd, shell=True)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+def export_coreml(model, im, file, prefix=colorstr('CoreML:')):
+    # YOLOv5 CoreML export
+    try:
+        check_requirements(('coremltools',))
+        import coremltools as ct
+
+        LOGGER.info(f'\n{prefix} starting export with coremltools {ct.__version__}...')
+        f = file.with_suffix('.mlmodel')
+
+        ts = torch.jit.trace(model, im, strict=False)  # TorchScript model
+        ct_model = ct.convert(ts, inputs=[ct.ImageType('image', shape=im.shape, scale=1 / 255, bias=[0, 0, 0])])
+        ct_model.save(f)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return ct_model, f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+        return None, None
+
+
+def export_engine(model, im, file, train, half, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:')):
+    # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt
+    try:
+        check_requirements(('tensorrt',))
+        import tensorrt as trt
+
+        if trt.__version__[0] == '7':  # TensorRT 7 handling https://github.com/ultralytics/yolov5/issues/6012
+            grid = model.model[-1].anchor_grid
+            model.model[-1].anchor_grid = [a[..., :1, :1, :] for a in grid]
+            export_onnx(model, im, file, 12, train, False, simplify)  # opset 12
+            model.model[-1].anchor_grid = grid
+        else:  # TensorRT >= 8
+            check_version(trt.__version__, '8.0.0', hard=True)  # require tensorrt>=8.0.0
+            export_onnx(model, im, file, 13, train, False, simplify)  # opset 13
+        onnx = file.with_suffix('.onnx')
+
+        LOGGER.info(f'\n{prefix} starting export with TensorRT {trt.__version__}...')
+        assert im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `python export.py --device 0`'
+        assert onnx.exists(), f'failed to export ONNX file: {onnx}'
+        f = file.with_suffix('.engine')  # TensorRT engine file
+        logger = trt.Logger(trt.Logger.INFO)
+        if verbose:
+            logger.min_severity = trt.Logger.Severity.VERBOSE
+
+        builder = trt.Builder(logger)
+        config = builder.create_builder_config()
+        config.max_workspace_size = workspace * 1 << 30
+
+        flag = (1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH))
+        network = builder.create_network(flag)
+        parser = trt.OnnxParser(network, logger)
+        if not parser.parse_from_file(str(onnx)):
+            raise RuntimeError(f'failed to load ONNX file: {onnx}')
+
+        inputs = [network.get_input(i) for i in range(network.num_inputs)]
+        outputs = [network.get_output(i) for i in range(network.num_outputs)]
+        LOGGER.info(f'{prefix} Network Description:')
+        for inp in inputs:
+            LOGGER.info(f'{prefix}\tinput "{inp.name}" with shape {inp.shape} and dtype {inp.dtype}')
+        for out in outputs:
+            LOGGER.info(f'{prefix}\toutput "{out.name}" with shape {out.shape} and dtype {out.dtype}')
+
+        half &= builder.platform_has_fast_fp16
+        LOGGER.info(f'{prefix} building FP{16 if half else 32} engine in {f}')
+        if half:
+            config.set_flag(trt.BuilderFlag.FP16)
+        with builder.build_engine(network, config) as engine, open(f, 'wb') as t:
+            t.write(engine.serialize())
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+def export_saved_model(model, im, file, dynamic,
+                       tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
+                       conf_thres=0.25, prefix=colorstr('TensorFlow SavedModel:')):
+    # YOLOv5 TensorFlow SavedModel export
+    try:
+        import tensorflow as tf
+        from tensorflow import keras
+
+        from models.tf import TFDetect, TFModel
+
+        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+        f = str(file).replace('.pt', '_saved_model')
+        batch_size, ch, *imgsz = list(im.shape)  # BCHW
+
+        tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+        im = tf.zeros((batch_size, *imgsz, 3))  # BHWC order for TensorFlow
+        _ = tf_model.predict(im, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
+        inputs = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
+        outputs = tf_model.predict(inputs, tf_nms, agnostic_nms, topk_per_class, topk_all, iou_thres, conf_thres)
+        keras_model = keras.Model(inputs=inputs, outputs=outputs)
+        keras_model.trainable = False
+        keras_model.summary()
+        keras_model.save(f, save_format='tf')
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return keras_model, f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+        return None, None
+
+
+def export_pb(keras_model, im, file, prefix=colorstr('TensorFlow GraphDef:')):
+    # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow
+    try:
+        import tensorflow as tf
+        from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
+
+        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+        f = file.with_suffix('.pb')
+
+        m = tf.function(lambda x: keras_model(x))  # full model
+        m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
+        frozen_func = convert_variables_to_constants_v2(m)
+        frozen_func.graph.as_graph_def()
+        tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+def export_tflite(keras_model, im, file, int8, data, ncalib, prefix=colorstr('TensorFlow Lite:')):
+    # YOLOv5 TensorFlow Lite export
+    try:
+        import tensorflow as tf
+
+        LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...')
+        batch_size, ch, *imgsz = list(im.shape)  # BCHW
+        f = str(file).replace('.pt', '-fp16.tflite')
+
+        converter = tf.lite.TFLiteConverter.from_keras_model(keras_model)
+        converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS]
+        converter.target_spec.supported_types = [tf.float16]
+        converter.optimizations = [tf.lite.Optimize.DEFAULT]
+        if int8:
+            from models.tf import representative_dataset_gen
+            dataset = LoadImages(check_dataset(data)['train'], img_size=imgsz, auto=False)  # representative data
+            converter.representative_dataset = lambda: representative_dataset_gen(dataset, ncalib)
+            converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
+            converter.target_spec.supported_types = []
+            converter.inference_input_type = tf.uint8  # or tf.int8
+            converter.inference_output_type = tf.uint8  # or tf.int8
+            converter.experimental_new_quantizer = False
+            f = str(file).replace('.pt', '-int8.tflite')
+
+        tflite_model = converter.convert()
+        open(f, "wb").write(tflite_model)
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+def export_edgetpu(keras_model, im, file, prefix=colorstr('Edge TPU:')):
+    # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/
+    try:
+        cmd = 'edgetpu_compiler --version'
+        help_url = 'https://coral.ai/docs/edgetpu/compiler/'
+        assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}'
+        if subprocess.run(cmd + ' >/dev/null', shell=True).returncode != 0:
+            LOGGER.info(f'\n{prefix} export requires Edge TPU compiler. Attempting install from {help_url}')
+            sudo = subprocess.run('sudo --version >/dev/null', shell=True).returncode == 0  # sudo installed on system
+            for c in ['curl https://packages.cloud.google.com/apt/doc/apt-key.gpg | sudo apt-key add -',
+                      'echo "deb https://packages.cloud.google.com/apt coral-edgetpu-stable main" | sudo tee /etc/apt/sources.list.d/coral-edgetpu.list',
+                      'sudo apt-get update',
+                      'sudo apt-get install edgetpu-compiler']:
+                subprocess.run(c if sudo else c.replace('sudo ', ''), shell=True, check=True)
+        ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().split()[-1]
+
+        LOGGER.info(f'\n{prefix} starting export with Edge TPU compiler {ver}...')
+        f = str(file).replace('.pt', '-int8_edgetpu.tflite')  # Edge TPU model
+        f_tfl = str(file).replace('.pt', '-int8.tflite')  # TFLite model
+
+        cmd = f"edgetpu_compiler -s {f_tfl}"
+        subprocess.run(cmd, shell=True, check=True)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+def export_tfjs(keras_model, im, file, prefix=colorstr('TensorFlow.js:')):
+    # YOLOv5 TensorFlow.js export
+    try:
+        check_requirements(('tensorflowjs',))
+        import re
+
+        import tensorflowjs as tfjs
+
+        LOGGER.info(f'\n{prefix} starting export with tensorflowjs {tfjs.__version__}...')
+        f = str(file).replace('.pt', '_web_model')  # js dir
+        f_pb = file.with_suffix('.pb')  # *.pb path
+        f_json = f + '/model.json'  # *.json path
+
+        cmd = f'tensorflowjs_converter --input_format=tf_frozen_model ' \
+              f'--output_node_names="Identity,Identity_1,Identity_2,Identity_3" {f_pb} {f}'
+        subprocess.run(cmd, shell=True)
+
+        json = open(f_json).read()
+        with open(f_json, 'w') as j:  # sort JSON Identity_* in ascending order
+            subst = re.sub(
+                r'{"outputs": {"Identity.?.?": {"name": "Identity.?.?"}, '
+                r'"Identity.?.?": {"name": "Identity.?.?"}, '
+                r'"Identity.?.?": {"name": "Identity.?.?"}, '
+                r'"Identity.?.?": {"name": "Identity.?.?"}}}',
+                r'{"outputs": {"Identity": {"name": "Identity"}, '
+                r'"Identity_1": {"name": "Identity_1"}, '
+                r'"Identity_2": {"name": "Identity_2"}, '
+                r'"Identity_3": {"name": "Identity_3"}}}',
+                json)
+            j.write(subst)
+
+        LOGGER.info(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return f
+    except Exception as e:
+        LOGGER.info(f'\n{prefix} export failure: {e}')
+
+
+@torch.no_grad()
+def run(data=ROOT / 'data/coco128.yaml',  # 'dataset.yaml path'
+        weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=(640, 640),  # image (height, width)
+        batch_size=1,  # batch size
+        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        include=('torchscript', 'onnx'),  # include formats
+        half=False,  # FP16 half-precision export
+        inplace=False,  # set YOLOv5 Detect() inplace=True
+        train=False,  # model.train() mode
+        optimize=False,  # TorchScript: optimize for mobile
+        int8=False,  # CoreML/TF INT8 quantization
+        dynamic=False,  # ONNX/TF: dynamic axes
+        simplify=False,  # ONNX: simplify model
+        opset=12,  # ONNX: opset version
+        verbose=False,  # TensorRT: verbose log
+        workspace=4,  # TensorRT: workspace size (GB)
+        nms=False,  # TF: add NMS to model
+        agnostic_nms=False,  # TF: add agnostic NMS to model
+        topk_per_class=100,  # TF.js NMS: topk per class to keep
+        topk_all=100,  # TF.js NMS: topk for all classes to keep
+        iou_thres=0.45,  # TF.js NMS: IoU threshold
+        conf_thres=0.25  # TF.js NMS: confidence threshold
+        ):
+    t = time.time()
+    include = [x.lower() for x in include]
+    tf_exports = list(x in include for x in ('saved_model', 'pb', 'tflite', 'edgetpu', 'tfjs'))  # TensorFlow exports
+    file = Path(url2file(weights) if str(weights).startswith(('http:/', 'https:/')) else weights)
+
+    # Load PyTorch model
+    device = select_device(device)
+    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
+    model = attempt_load(weights, map_location=device, inplace=True, fuse=True)  # load FP32 model
+    nc, names = model.nc, model.names  # number of classes, class names
+
+    # Checks
+    imgsz *= 2 if len(imgsz) == 1 else 1  # expand
+    opset = 12 if ('openvino' in include) else opset  # OpenVINO requires opset <= 12
+    assert nc == len(names), f'Model class count {nc} != len(names) {len(names)}'
+
+    # Input
+    gs = int(max(model.stride))  # grid size (max stride)
+    imgsz = [check_img_size(x, gs) for x in imgsz]  # verify img_size are gs-multiples
+    im = torch.zeros(batch_size, 3, *imgsz).to(device)  # image size(1,3,320,192) BCHW iDetection
+
+    # Update model
+    if half:
+        im, model = im.half(), model.half()  # to FP16
+    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
+    for k, m in model.named_modules():
+        if isinstance(m, Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        elif isinstance(m, Detect):
+            m.inplace = inplace
+            m.onnx_dynamic = dynamic
+            if hasattr(m, 'forward_export'):
+                m.forward = m.forward_export  # assign custom forward (optional)
+
+    for _ in range(2):
+        y = model(im)  # dry runs
+    shape = tuple(y[0].shape)  # model output shape
+    LOGGER.info(f"\n{colorstr('PyTorch:')} starting from {file} with output shape {shape} ({file_size(file):.1f} MB)")
+
+    # Exports
+    f = [''] * 10  # exported filenames
+    warnings.filterwarnings(action='ignore', category=torch.jit.TracerWarning)  # suppress TracerWarning
+    if 'torchscript' in include:
+        f[0] = export_torchscript(model, im, file, optimize)
+    if 'engine' in include:  # TensorRT required before ONNX
+        f[1] = export_engine(model, im, file, train, half, simplify, workspace, verbose)
+    if ('onnx' in include) or ('openvino' in include):  # OpenVINO requires ONNX
+        f[2] = export_onnx(model, im, file, opset, train, dynamic, simplify)
+    if 'openvino' in include:
+        f[3] = export_openvino(model, im, file)
+    if 'coreml' in include:
+        _, f[4] = export_coreml(model, im, file)
+
+    # TensorFlow Exports
+    if any(tf_exports):
+        pb, tflite, edgetpu, tfjs = tf_exports[1:]
+        if int8 or edgetpu:  # TFLite --int8 bug https://github.com/ultralytics/yolov5/issues/5707
+            check_requirements(('flatbuffers==1.12',))  # required before `import tensorflow`
+        assert not (tflite and tfjs), 'TFLite and TF.js models must be exported separately, please pass only one type.'
+        model, f[5] = export_saved_model(model, im, file, dynamic, tf_nms=nms or agnostic_nms or tfjs,
+                                         agnostic_nms=agnostic_nms or tfjs, topk_per_class=topk_per_class,
+                                         topk_all=topk_all, conf_thres=conf_thres, iou_thres=iou_thres)  # keras model
+        if pb or tfjs:  # pb prerequisite to tfjs
+            f[6] = export_pb(model, im, file)
+        if tflite or edgetpu:
+            f[7] = export_tflite(model, im, file, int8=int8 or edgetpu, data=data, ncalib=100)
+        if edgetpu:
+            f[8] = export_edgetpu(model, im, file)
+        if tfjs:
+            f[9] = export_tfjs(model, im, file)
+
+    # Finish
+    f = [str(x) for x in f if x]  # filter out '' and None
+    if any(f):
+        LOGGER.info(f'\nExport complete ({time.time() - t:.2f}s)'
+                    f"\nResults saved to {colorstr('bold', file.parent.resolve())}"
+                    f"\nDetect:          python detect.py --weights {f[-1]}"
+                    f"\nPyTorch Hub:     model = torch.hub.load('ultralytics/yolov5', 'custom', '{f[-1]}')"
+                    f"\nValidate:        python val.py --weights {f[-1]}"
+                    f"\nVisualize:       https://netron.app")
+    return f  # return list of exported files/dirs
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
+    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640, 640], help='image (h, w)')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
+    parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True')
+    parser.add_argument('--train', action='store_true', help='model.train() mode')
+    parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile')
+    parser.add_argument('--int8', action='store_true', help='CoreML/TF INT8 quantization')
+    parser.add_argument('--dynamic', action='store_true', help='ONNX/TF: dynamic axes')
+    parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model')
+    parser.add_argument('--opset', type=int, default=12, help='ONNX: opset version')
+    parser.add_argument('--verbose', action='store_true', help='TensorRT: verbose log')
+    parser.add_argument('--workspace', type=int, default=4, help='TensorRT: workspace size (GB)')
+    parser.add_argument('--nms', action='store_true', help='TF: add NMS to model')
+    parser.add_argument('--agnostic-nms', action='store_true', help='TF: add agnostic NMS to model')
+    parser.add_argument('--topk-per-class', type=int, default=100, help='TF.js NMS: topk per class to keep')
+    parser.add_argument('--topk-all', type=int, default=100, help='TF.js NMS: topk for all classes to keep')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='TF.js NMS: IoU threshold')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='TF.js NMS: confidence threshold')
+    parser.add_argument('--include', nargs='+',
+                        default=['torchscript', 'onnx'],
+                        help='torchscript, onnx, openvino, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs')
+    opt = parser.parse_args()
+    print_args(FILE.stem, opt)
+    return opt
+
+
+def main(opt):
+    for opt.weights in (opt.weights if isinstance(opt.weights, list) else [opt.weights]):
+        run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

yolov5/models/common.py

@@ -0,0 +1,674 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Common modules
+"""
+
+import json
+import math
+import platform
+import warnings
+from collections import OrderedDict, namedtuple
+from copy import copy
+from pathlib import Path
+
+import cv2
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+import yaml
+from PIL import Image
+from torch.cuda import amp
+
+from yolov5.utils.datasets import exif_transpose
+from yolov5.utils.augmentations import letterbox
+from yolov5.utils.general import (LOGGER, check_requirements, check_suffix, check_version, colorstr, increment_path,
+                           make_divisible, non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh)
+from yolov5.utils.plots import Annotator, colors, save_one_box
+from yolov5.utils.torch_utils import copy_attr, time_sync
+
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def forward_fuse(self, x):
+        return self.act(self.conv(x))
+
+
+class DWConv(Conv):
+    # Depth-wise convolution class
+    def __init__(self, c1, c2, k=1, s=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2).permute(2, 0, 1)
+        return self.tr(p + self.linear(p)).permute(1, 2, 0).reshape(b, self.c2, w, h)
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.SiLU()
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class C3TR(C3):
+    # C3 module with TransformerBlock()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class C3SPP(C3):
+    # C3 module with SPP()
+    def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = SPP(c_, c_, k)
+
+
+class C3Ghost(C3):
+    # C3 module with GhostBottleneck()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
+
+
+class SPP(nn.Module):
+    # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        with warnings.catch_warnings():
+            warnings.simplefilter('ignore')  # suppress torch 1.9.0 max_pool2d() warning
+            y1 = self.m(x)
+            y2 = self.m(y1)
+            return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+        # return self.conv(self.contract(x))
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super().__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat([y, self.cv2(y)], 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super().__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
+                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, c, h // s, s, w // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(b, c * s * s, h // s, w // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        b, c, h, w = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(b, s, s, c // s ** 2, h, w)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(b, c // s ** 2, h * s, w * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super().__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class DetectMultiBackend(nn.Module):
+    # YOLOv5 MultiBackend class for python inference on various backends
+    def __init__(self, weights='yolov5s.pt', device=None, dnn=False, data=None):
+        # Usage:
+        #   PyTorch:      weights = *.pt
+        #   TorchScript:            *.torchscript
+        #   CoreML:                 *.mlmodel
+        #   OpenVINO:               *.xml
+        #   TensorFlow:             *_saved_model
+        #   TensorFlow:             *.pb
+        #   TensorFlow Lite:        *.tflite
+        #   TensorFlow Edge TPU:    *_edgetpu.tflite
+        #   ONNX Runtime:           *.onnx
+        #   OpenCV DNN:             *.onnx with dnn=True
+        #   TensorRT:               *.engine
+        from yolov5.models.experimental import attempt_download, attempt_load  # scoped to avoid circular import
+
+        super().__init__()
+        w = str(weights[0] if isinstance(weights, list) else weights)
+        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs = self.model_type(w)  # get backend
+        stride, names = 64, [f'class{i}' for i in range(1000)]  # assign defaults
+        w = attempt_download(w)  # download if not local
+        if data:  # data.yaml path (optional)
+            with open(data, errors='ignore') as f:
+                names = yaml.safe_load(f)['names']  # class names
+
+        if pt:  # PyTorch
+            model = attempt_load(weights if isinstance(weights, list) else w, map_location=device)
+            stride = max(int(model.stride.max()), 32)  # model stride
+            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
+            self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
+        elif jit:  # TorchScript
+            LOGGER.info(f'Loading {w} for TorchScript inference...')
+            extra_files = {'config.txt': ''}  # model metadata
+            model = torch.jit.load(w, _extra_files=extra_files)
+            if extra_files['config.txt']:
+                d = json.loads(extra_files['config.txt'])  # extra_files dict
+                stride, names = int(d['stride']), d['names']
+        elif dnn:  # ONNX OpenCV DNN
+            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
+            check_requirements(('opencv-python>=4.5.4',))
+            net = cv2.dnn.readNetFromONNX(w)
+        elif onnx:  # ONNX Runtime
+            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
+            cuda = torch.cuda.is_available()
+            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
+            import onnxruntime
+            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+            session = onnxruntime.InferenceSession(w, providers=providers)
+        elif xml:  # OpenVINO
+            LOGGER.info(f'Loading {w} for OpenVINO inference...')
+            check_requirements(('openvino-dev',))  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+            import openvino.inference_engine as ie
+            core = ie.IECore()
+            if not Path(w).is_file():  # if not *.xml
+                w = next(Path(w).glob('*.xml'))  # get *.xml file from *_openvino_model dir
+            network = core.read_network(model=w, weights=Path(w).with_suffix('.bin'))  # *.xml, *.bin paths
+            executable_network = core.load_network(network, device_name='CPU', num_requests=1)
+        elif engine:  # TensorRT
+            LOGGER.info(f'Loading {w} for TensorRT inference...')
+            import tensorrt as trt  # https://developer.nvidia.com/nvidia-tensorrt-download
+            check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
+            Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
+            logger = trt.Logger(trt.Logger.INFO)
+            with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
+                model = runtime.deserialize_cuda_engine(f.read())
+            bindings = OrderedDict()
+            for index in range(model.num_bindings):
+                name = model.get_binding_name(index)
+                dtype = trt.nptype(model.get_binding_dtype(index))
+                shape = tuple(model.get_binding_shape(index))
+                data = torch.from_numpy(np.empty(shape, dtype=np.dtype(dtype))).to(device)
+                bindings[name] = Binding(name, dtype, shape, data, int(data.data_ptr()))
+            binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
+            context = model.create_execution_context()
+            batch_size = bindings['images'].shape[0]
+        elif coreml:  # CoreML
+            LOGGER.info(f'Loading {w} for CoreML inference...')
+            import coremltools as ct
+            model = ct.models.MLModel(w)
+        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
+            if saved_model:  # SavedModel
+                LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
+                import tensorflow as tf
+                model = tf.keras.models.load_model(w)
+            elif pb:  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
+                LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
+                import tensorflow as tf
+
+                def wrap_frozen_graph(gd, inputs, outputs):
+                    x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped
+                    return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
+                                   tf.nest.map_structure(x.graph.as_graph_element, outputs))
+
+                graph_def = tf.Graph().as_graph_def()
+                graph_def.ParseFromString(open(w, 'rb').read())
+                frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
+            elif tflite:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
+                try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
+                    from tflite_runtime.interpreter import Interpreter, load_delegate
+                except ImportError:
+                    import tensorflow as tf
+                    Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate,
+                if 'edgetpu' in w.lower():  # Edge TPU https://coral.ai/software/#edgetpu-runtime
+                    LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
+                    delegate = {'Linux': 'libedgetpu.so.1',
+                                'Darwin': 'libedgetpu.1.dylib',
+                                'Windows': 'edgetpu.dll'}[platform.system()]
+                    interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
+                else:  # Lite
+                    LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
+                    interpreter = Interpreter(model_path=w)  # load TFLite model
+                interpreter.allocate_tensors()  # allocate
+                input_details = interpreter.get_input_details()  # inputs
+                output_details = interpreter.get_output_details()  # outputs
+        self.__dict__.update(locals())  # assign all variables to self
+
+    def forward(self, im, augment=False, visualize=False, val=False):
+        # YOLOv5 MultiBackend inference
+        b, ch, h, w = im.shape  # batch, channel, height, width
+        if self.pt or self.jit:  # PyTorch
+            y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize)
+            return y if val else y[0]
+        elif self.dnn:  # ONNX OpenCV DNN
+            im = im.cpu().numpy()  # torch to numpy
+            self.net.setInput(im)
+            y = self.net.forward()
+        elif self.onnx:  # ONNX Runtime
+            im = im.cpu().numpy()  # torch to numpy
+            y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0]
+        elif self.xml:  # OpenVINO
+            im = im.cpu().numpy()  # FP32
+            desc = self.ie.TensorDesc(precision='FP32', dims=im.shape, layout='NCHW')  # Tensor Description
+            request = self.executable_network.requests[0]  # inference request
+            request.set_blob(blob_name='images', blob=self.ie.Blob(desc, im))  # name=next(iter(request.input_blobs))
+            request.infer()
+            y = request.output_blobs['output'].buffer  # name=next(iter(request.output_blobs))
+        elif self.engine:  # TensorRT
+            assert im.shape == self.bindings['images'].shape, (im.shape, self.bindings['images'].shape)
+            self.binding_addrs['images'] = int(im.data_ptr())
+            self.context.execute_v2(list(self.binding_addrs.values()))
+            y = self.bindings['output'].data
+        elif self.coreml:  # CoreML
+            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
+            im = Image.fromarray((im[0] * 255).astype('uint8'))
+            # im = im.resize((192, 320), Image.ANTIALIAS)
+            y = self.model.predict({'image': im})  # coordinates are xywh normalized
+            if 'confidence' in y:
+                box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
+                conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
+                y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
+            else:
+                y = y[sorted(y)[-1]]  # last output
+        else:  # TensorFlow (SavedModel, GraphDef, Lite, Edge TPU)
+            im = im.permute(0, 2, 3, 1).cpu().numpy()  # torch BCHW to numpy BHWC shape(1,320,192,3)
+            if self.saved_model:  # SavedModel
+                y = self.model(im, training=False).numpy()
+            elif self.pb:  # GraphDef
+                y = self.frozen_func(x=self.tf.constant(im)).numpy()
+            elif self.tflite:  # Lite
+                input, output = self.input_details[0], self.output_details[0]
+                int8 = input['dtype'] == np.uint8  # is TFLite quantized uint8 model
+                if int8:
+                    scale, zero_point = input['quantization']
+                    im = (im / scale + zero_point).astype(np.uint8)  # de-scale
+                self.interpreter.set_tensor(input['index'], im)
+                self.interpreter.invoke()
+                y = self.interpreter.get_tensor(output['index'])
+                if int8:
+                    scale, zero_point = output['quantization']
+                    y = (y.astype(np.float32) - zero_point) * scale  # re-scale
+            y[..., :4] *= [w, h, w, h]  # xywh normalized to pixels
+
+        y = torch.tensor(y) if isinstance(y, np.ndarray) else y
+        return (y, []) if val else y
+
+    def warmup(self, imgsz=(1, 3, 640, 640), half=False):
+        # Warmup model by running inference once
+        if self.pt or self.jit or self.onnx or self.engine:  # warmup types
+            if isinstance(self.device, torch.device) and self.device.type != 'cpu':  # only warmup GPU models
+                im = torch.zeros(*imgsz).to(self.device).type(torch.half if half else torch.float)  # input image
+                self.forward(im)  # warmup
+
+    @staticmethod
+    def model_type(p='path/to/model.pt'):
+        # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
+        from yolov5.export import export_formats
+        suffixes = list(export_formats().Suffix) + ['.xml']  # export suffixes
+        check_suffix(p, suffixes)  # checks
+        p = Path(p).name  # eliminate trailing separators
+        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, xml2 = (s in p for s in suffixes)
+        xml |= xml2  # *_openvino_model or *.xml
+        tflite &= not edgetpu  # *.tflite
+        return pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs
+
+
+class AutoShape(nn.Module):
+    # YOLOv5 input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    agnostic = False  # NMS class-agnostic
+    multi_label = False  # NMS multiple labels per box
+    classes = None  # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
+    max_det = 1000  # maximum number of detections per image
+    amp = False  # Automatic Mixed Precision (AMP) inference
+
+    def __init__(self, model):
+        super().__init__()
+        LOGGER.info('Adding AutoShape... ')
+        copy_attr(self, model, include=('yaml', 'nc', 'hyp', 'names', 'stride', 'abc'), exclude=())  # copy attributes
+        self.dmb = isinstance(model, DetectMultiBackend)  # DetectMultiBackend() instance
+        self.pt = not self.dmb or model.pt  # PyTorch model
+        self.model = model.eval()
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        if self.pt:
+            m = self.model.model.model[-1] if self.dmb else self.model.model[-1]  # Detect()
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+    @torch.no_grad()
+    def forward(self, imgs, size=640, augment=False, profile=False):
+        # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
+        #   file:       imgs = 'data/images/zidane.jpg'  # str or PosixPath
+        #   URI:             = 'https://ultralytics.com/images/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg') or ImageGrab.grab()  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        t = [time_sync()]
+        p = next(self.model.parameters()) if self.pt else torch.zeros(1)  # for device and type
+        autocast = self.amp and (p.device.type != 'cpu')  # Automatic Mixed Precision (AMP) inference
+        if isinstance(imgs, torch.Tensor):  # torch
+            with amp.autocast(enabled=autocast):
+                return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
+
+        # Pre-process
+        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
+        shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+        for i, im in enumerate(imgs):
+            f = f'image{i}'  # filename
+            if isinstance(im, (str, Path)):  # filename or uri
+                im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
+                im = np.asarray(exif_transpose(im))
+            elif isinstance(im, Image.Image):  # PIL Image
+                im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
+            files.append(Path(f).with_suffix('.jpg').name)
+            if im.shape[0] < 5:  # image in CHW
+                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+            im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3)  # enforce 3ch input
+            s = im.shape[:2]  # HWC
+            shape0.append(s)  # image shape
+            g = (size / max(s))  # gain
+            shape1.append([y * g for y in s])
+            imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
+        shape1 = [make_divisible(x, self.stride) for x in np.stack(shape1, 0).max(0)]  # inference shape
+        x = [letterbox(im, new_shape=shape1 if self.pt else size, auto=False)[0] for im in imgs]  # pad
+        x = np.stack(x, 0) if n > 1 else x[0][None]  # stack
+        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
+        x = torch.from_numpy(x).to(p.device).type_as(p) / 255  # uint8 to fp16/32
+        t.append(time_sync())
+
+        with amp.autocast(enabled=autocast):
+            # Inference
+            y = self.model(x, augment, profile)  # forward
+            t.append(time_sync())
+
+            # Post-process
+            y = non_max_suppression(y if self.dmb else y[0], self.conf, iou_thres=self.iou, classes=self.classes,
+                                    agnostic=self.agnostic, multi_label=self.multi_label, max_det=self.max_det)  # NMS
+            for i in range(n):
+                scale_coords(shape1, y[i][:, :4], shape0[i])
+
+            t.append(time_sync())
+            return Detections(imgs, y, files, t, self.names, x.shape)
+
+
+class Detections:
+    # YOLOv5 detections class for inference results
+    def __init__(self, imgs, pred, files, times=(0, 0, 0, 0), names=None, shape=None):
+        super().__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs]  # normalizations
+        self.imgs = imgs  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.times = times  # profiling times
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3))  # timestamps (ms)
+        self.s = shape  # inference BCHW shape
+
+    def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
+        crops = []
+        for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
+            s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
+            if pred.shape[0]:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                if show or save or render or crop:
+                    annotator = Annotator(im, example=str(self.names))
+                    for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        if crop:
+                            file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
+                            crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
+                                          'im': save_one_box(box, im, file=file, save=save)})
+                        else:  # all others
+                            annotator.box_label(box, label, color=colors(cls))
+                    im = annotator.im
+            else:
+                s += '(no detections)'
+
+            im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
+            if pprint:
+                LOGGER.info(s.rstrip(', '))
+            if show:
+                im.show(self.files[i])  # show
+            if save:
+                f = self.files[i]
+                im.save(save_dir / f)  # save
+                if i == self.n - 1:
+                    LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
+            if render:
+                self.imgs[i] = np.asarray(im)
+        if crop:
+            if save:
+                LOGGER.info(f'Saved results to {save_dir}\n')
+            return crops
+
+    def print(self):
+        self.display(pprint=True)  # print results
+        LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
+                    self.t)
+
+    def show(self):
+        self.display(show=True)  # show results
+
+    def save(self, save_dir='runs/detect/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True)  # increment save_dir
+        self.display(save=True, save_dir=save_dir)  # save results
+
+    def crop(self, save=True, save_dir='runs/detect/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
+        return self.display(crop=True, save=save, save_dir=save_dir)  # crop results
+
+    def render(self):
+        self.display(render=True)  # render results
+        return self.imgs
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        r = range(self.n)  # iterable
+        x = [Detections([self.imgs[i]], [self.pred[i]], [self.files[i]], self.times, self.names, self.s) for i in r]
+        # for d in x:
+        #    for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+        #        setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def __len__(self):
+        return self.n
+
+
+class Classify(nn.Module):
+    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
+        self.flat = nn.Flatten()
+
+    def forward(self, x):
+        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
+        return self.flat(self.conv(z))  # flatten to x(b,c2)

yolov5/models/experimental.py

@@ -0,0 +1,120 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+Experimental modules
+"""
+import math
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from yolov5.models.common import Conv
+from yolov5.utils.downloads import attempt_download
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super().__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):  # ch_in, ch_out, kernel, stride, ch_strategy
+        super().__init__()
+        n = len(k)  # number of convolutions
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, n - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(n)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * n
+            a = np.eye(n + 1, n, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList(
+            [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU()
+
+    def forward(self, x):
+        return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super().__init__()
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        y = []
+        for module in self:
+            y.append(module(x, augment, profile, visualize)[0])
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, map_location=None, inplace=True, fuse=True):
+    from models.yolo import Detect, Model
+
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        ckpt = torch.load(attempt_download(w), map_location=map_location)  # load
+        if fuse:
+            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model
+        else:
+            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval())  # without layer fuse
+
+    # Compatibility updates
+    for m in model.modules():
+        if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
+            m.inplace = inplace  # pytorch 1.7.0 compatibility
+            if type(m) is Detect:
+                if not isinstance(m.anchor_grid, list):  # new Detect Layer compatibility
+                    delattr(m, 'anchor_grid')
+                    setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
+        elif type(m) is Conv:
+            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print(f'Ensemble created with {weights}\n')
+        for k in ['names']:
+            setattr(model, k, getattr(model[-1], k))
+        model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
+        return model  # return ensemble

yolov5/models/hub/anchors.yaml

@@ -0,0 +1,59 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+# Default anchors for COCO data
+
+
+# P5 -------------------------------------------------------------------------------------------------------------------
+# P5-640:
+anchors_p5_640:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+
+# P6 -------------------------------------------------------------------------------------------------------------------
+# P6-640:  thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11,  21,19,  17,41,  43,32,  39,70,  86,64,  65,131,  134,130,  120,265,  282,180,  247,354,  512,387
+anchors_p6_640:
+  - [9,11,  21,19,  17,41]  # P3/8
+  - [43,32,  39,70,  86,64]  # P4/16
+  - [65,131,  134,130,  120,265]  # P5/32
+  - [282,180,  247,354,  512,387]  # P6/64
+
+# P6-1280:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27,  44,40,  38,94,  96,68,  86,152,  180,137,  140,301,  303,264,  238,542,  436,615,  739,380,  925,792
+anchors_p6_1280:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# P6-1920:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41,  67,59,  57,141,  144,103,  129,227,  270,205,  209,452,  455,396,  358,812,  653,922,  1109,570,  1387,1187
+anchors_p6_1920:
+  - [28,41,  67,59,  57,141]  # P3/8
+  - [144,103,  129,227,  270,205]  # P4/16
+  - [209,452,  455,396,  358,812]  # P5/32
+  - [653,922,  1109,570,  1387,1187]  # P6/64
+
+
+# P7 -------------------------------------------------------------------------------------------------------------------
+# P7-640:  thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11,  13,30,  29,20,  30,46,  61,38,  39,92,  78,80,  146,66,  79,163,  149,150,  321,143,  157,303,  257,402,  359,290,  524,372
+anchors_p7_640:
+  - [11,11,  13,30,  29,20]  # P3/8
+  - [30,46,  61,38,  39,92]  # P4/16
+  - [78,80,  146,66,  79,163]  # P5/32
+  - [149,150,  321,143,  157,303]  # P6/64
+  - [257,402,  359,290,  524,372]  # P7/128
+
+# P7-1280:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22,  54,36,  32,77,  70,83,  138,71,  75,173,  165,159,  148,334,  375,151,  334,317,  251,626,  499,474,  750,326,  534,814,  1079,818
+anchors_p7_1280:
+  - [19,22,  54,36,  32,77]  # P3/8
+  - [70,83,  138,71,  75,173]  # P4/16
+  - [165,159,  148,334,  375,151]  # P5/32
+  - [334,317,  251,626,  499,474]  # P6/64
+  - [750,326,  534,814,  1079,818]  # P7/128
+
+# P7-1920:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34,  81,55,  47,115,  105,124,  207,107,  113,259,  247,238,  222,500,  563,227,  501,476,  376,939,  749,711,  1126,489,  801,1222,  1618,1227
+anchors_p7_1920:
+  - [29,34,  81,55,  47,115]  # P3/8
+  - [105,124,  207,107,  113,259]  # P4/16
+  - [247,238,  222,500,  563,227]  # P5/32
+  - [501,476,  376,939,  749,711]  # P6/64
+  - [1126,489,  801,1222,  1618,1227]  # P7/128

yolov5/models/hub/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov3-tiny.yaml

@@ -0,0 +1,41 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,14, 23,27, 37,58]  # P4/16
+  - [81,82, 135,169, 344,319]  # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [16, 3, 1]],  # 0
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
+   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
+  ]
+
+# YOLOv3-tiny head
+head:
+  [[-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
+
+   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
+  ]

yolov5/models/hub/yolov3.yaml

@@ -0,0 +1,51 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-bifpn.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 BiFPN head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14, 6], 1, Concat, [1]],  # cat P4 <--- BiFPN change
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-fpn.yaml

@@ -0,0 +1,42 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 FPN head
+head:
+  [[-1, 3, C3, [1024, False]],  # 10 (P5/32-large)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 3, C3, [512, False]],  # 14 (P4/16-medium)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 3, C3, [256, False]],  # 18 (P3/8-small)
+
+   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-p2.yaml

@@ -0,0 +1,54 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 2], 1, Concat, [1]],  # cat backbone P2
+   [-1, 1, C3, [128, False]],  # 21 (P2/4-xsmall)
+
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P3
+   [-1, 3, C3, [256, False]],  # 24 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 27 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 30 (P5/32-large)
+
+   [[21, 24, 27, 30], 1, Detect, [nc, anchors]],  # Detect(P2, P3, P4, P5)
+  ]

yolov5/models/hub/yolov5-p34.yaml

@@ -0,0 +1,41 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Conv, [ 64, 6, 2, 2 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 6, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 1024 ] ],
+    [ -1, 1, SPPF, [ 1024, 5 ] ],  # 9
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4) outputs
+head:
+  [ [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 13
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 17 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 14 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 20 (P4/16-medium)
+
+    [ [ 17, 20 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4)
+  ]

yolov5/models/hub/yolov5-p6.yaml

@@ -0,0 +1,56 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/hub/yolov5-p7.yaml

@@ -0,0 +1,67 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors: 3  # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, Conv, [1280, 3, 2]],  # 11-P7/128
+   [-1, 3, C3, [1280]],
+   [-1, 1, SPPF, [1280, 5]],  # 13
+  ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs
+head:
+  [[-1, 1, Conv, [1024, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 10], 1, Concat, [1]],  # cat backbone P6
+   [-1, 3, C3, [1024, False]],  # 17
+
+   [-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 21
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 25
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 29 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 26], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 32 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 35 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 18], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 38 (P6/64-xlarge)
+
+   [-1, 1, Conv, [1024, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P7
+   [-1, 3, C3, [1280, False]],  # 41 (P7/128-xxlarge)
+
+   [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6, P7)
+  ]

yolov5/models/hub/yolov5-panet.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 PANet head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5l6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/hub/yolov5m6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/hub/yolov5n6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/hub/yolov5s-ghost.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, GhostConv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3Ghost, [128]],
+   [-1, 1, GhostConv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3Ghost, [256]],
+   [-1, 1, GhostConv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3Ghost, [512]],
+   [-1, 1, GhostConv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3Ghost, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, GhostConv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3Ghost, [512, False]],  # 13
+
+   [-1, 1, GhostConv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3Ghost, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, GhostConv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3Ghost, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, GhostConv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3Ghost, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5s-transformer.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3TR, [1024]],  # 9 <--- C3TR() Transformer module
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/hub/yolov5s6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/hub/yolov5x6.yaml

@@ -0,0 +1,60 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [19,27,  44,40,  38,94]  # P3/8
+  - [96,68,  86,152,  180,137]  # P4/16
+  - [140,301,  303,264,  238,542]  # P5/32
+  - [436,615,  739,380,  925,792]  # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [768, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [768]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P6/64
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 11
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [768, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P5
+   [-1, 3, C3, [768, False]],  # 15
+
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 19
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 23 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 20], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 26 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [768, False]],  # 29 (P5/32-large)
+
+   [-1, 1, Conv, [768, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat head P6
+   [-1, 3, C3, [1024, False]],  # 32 (P6/64-xlarge)
+
+   [[23, 26, 29, 32], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5, P6)
+  ]

yolov5/models/tf.py

@@ -0,0 +1,464 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+TensorFlow, Keras and TFLite versions of YOLOv5
+Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
+
+Usage:
+    $ python models/tf.py --weights yolov5s.pt
+
+Export:
+    $ python path/to/export.py --weights yolov5s.pt --include saved_model pb tflite tfjs
+"""
+
+import argparse
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+import numpy as np
+import tensorflow as tf
+import torch
+import torch.nn as nn
+from tensorflow import keras
+
+from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad
+from models.experimental import CrossConv, MixConv2d, attempt_load
+from models.yolo import Detect
+from utils.activations import SiLU
+from utils.general import LOGGER, make_divisible, print_args
+
+
+class TFBN(keras.layers.Layer):
+    # TensorFlow BatchNormalization wrapper
+    def __init__(self, w=None):
+        super().__init__()
+        self.bn = keras.layers.BatchNormalization(
+            beta_initializer=keras.initializers.Constant(w.bias.numpy()),
+            gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
+            moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
+            moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
+            epsilon=w.eps)
+
+    def call(self, inputs):
+        return self.bn(inputs)
+
+
+class TFPad(keras.layers.Layer):
+    def __init__(self, pad):
+        super().__init__()
+        self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
+
+    def call(self, inputs):
+        return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
+
+
+class TFConv(keras.layers.Layer):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, weights, kernel, stride, padding, groups
+        super().__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
+        # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
+        # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
+
+        conv = keras.layers.Conv2D(
+            c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
+            kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
+        self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
+        self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
+
+        # YOLOv5 activations
+        if isinstance(w.act, nn.LeakyReLU):
+            self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
+        elif isinstance(w.act, nn.Hardswish):
+            self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
+        elif isinstance(w.act, (nn.SiLU, SiLU)):
+            self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
+        else:
+            raise Exception(f'no matching TensorFlow activation found for {w.act}')
+
+    def call(self, inputs):
+        return self.act(self.bn(self.conv(inputs)))
+
+
+class TFFocus(keras.layers.Layer):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+        # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__()
+        self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
+
+    def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
+        # inputs = inputs / 255  # normalize 0-255 to 0-1
+        return self.conv(tf.concat([inputs[:, ::2, ::2, :],
+                                    inputs[:, 1::2, ::2, :],
+                                    inputs[:, ::2, 1::2, :],
+                                    inputs[:, 1::2, 1::2, :]], 3))
+
+
+class TFBottleneck(keras.layers.Layer):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
+        self.add = shortcut and c1 == c2
+
+    def call(self, inputs):
+        return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
+
+
+class TFConv2d(keras.layers.Layer):
+    # Substitution for PyTorch nn.Conv2D
+    def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
+        super().__init__()
+        assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+        self.conv = keras.layers.Conv2D(
+            c2, k, s, 'VALID', use_bias=bias,
+            kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
+            bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
+
+    def call(self, inputs):
+        return self.conv(inputs)
+
+
+class TFBottleneckCSP(keras.layers.Layer):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
+        self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
+        self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
+        self.bn = TFBN(w.bn)
+        self.act = lambda x: keras.activations.relu(x, alpha=0.1)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        y1 = self.cv3(self.m(self.cv1(inputs)))
+        y2 = self.cv2(inputs)
+        return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
+
+
+class TFC3(keras.layers.Layer):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+        # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
+        self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
+        self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+    def call(self, inputs):
+        return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
+
+
+class TFSPP(keras.layers.Layer):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13), w=None):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
+        self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
+
+
+class TFSPPF(keras.layers.Layer):
+    # Spatial pyramid pooling-Fast layer
+    def __init__(self, c1, c2, k=5, w=None):
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+        self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
+        self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
+
+    def call(self, inputs):
+        x = self.cv1(inputs)
+        y1 = self.m(x)
+        y2 = self.m(y1)
+        return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
+
+
+class TFDetect(keras.layers.Layer):
+    def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
+        super().__init__()
+        self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [tf.zeros(1)] * self.nl  # init grid
+        self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
+        self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
+                                      [self.nl, 1, -1, 1, 2])
+        self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
+        self.training = False  # set to False after building model
+        self.imgsz = imgsz
+        for i in range(self.nl):
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            self.grid[i] = self._make_grid(nx, ny)
+
+    def call(self, inputs):
+        z = []  # inference output
+        x = []
+        for i in range(self.nl):
+            x.append(self.m[i](inputs[i]))
+            # x(bs,20,20,255) to x(bs,3,20,20,85)
+            ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+            x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
+
+            if not self.training:  # inference
+                y = tf.sigmoid(x[i])
+                xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
+                # Normalize xywh to 0-1 to reduce calibration error
+                xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+                y = tf.concat([xy, wh, y[..., 4:]], -1)
+                z.append(tf.reshape(y, [-1, self.na * ny * nx, self.no]))
+
+        return x if self.training else (tf.concat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+        xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
+        return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
+
+
+class TFUpsample(keras.layers.Layer):
+    def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
+        super().__init__()
+        assert scale_factor == 2, "scale_factor must be 2"
+        self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
+        # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
+        # with default arguments: align_corners=False, half_pixel_centers=False
+        # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
+        #                                                            size=(x.shape[1] * 2, x.shape[2] * 2))
+
+    def call(self, inputs):
+        return self.upsample(inputs)
+
+
+class TFConcat(keras.layers.Layer):
+    def __init__(self, dimension=1, w=None):
+        super().__init__()
+        assert dimension == 1, "convert only NCHW to NHWC concat"
+        self.d = 3
+
+    def call(self, inputs):
+        return tf.concat(inputs, self.d)
+
+
+def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m_str = m
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except NameError:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
+            c1, c2 = ch[f], args[0]
+            c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3]:
+                args.insert(2, n)
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
+        elif m is Detect:
+            args.append([ch[x + 1] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+            args.append(imgsz)
+        else:
+            c2 = ch[f]
+
+        tf_m = eval('TF' + m_str.replace('nn.', ''))
+        m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
+            else tf_m(*args, w=model.model[i])  # module
+
+        torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum(x.numel() for x in torch_m_.parameters())  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10}  {t:<40}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        ch.append(c2)
+    return keras.Sequential(layers), sorted(save)
+
+
+class TFModel:
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+
+        # Define model
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
+
+    def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
+                conf_thres=0.25):
+        y = []  # outputs
+        x = inputs
+        for i, m in enumerate(self.model.layers):
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            x = m(x)  # run
+            y.append(x if m.i in self.savelist else None)  # save output
+
+        # Add TensorFlow NMS
+        if tf_nms:
+            boxes = self._xywh2xyxy(x[0][..., :4])
+            probs = x[0][:, :, 4:5]
+            classes = x[0][:, :, 5:]
+            scores = probs * classes
+            if agnostic_nms:
+                nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
+                return nms, x[1]
+            else:
+                boxes = tf.expand_dims(boxes, 2)
+                nms = tf.image.combined_non_max_suppression(
+                    boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
+                return nms, x[1]
+
+        return x[0]  # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
+        # x = x[0][0]  # [x(1,6300,85), ...] to x(6300,85)
+        # xywh = x[..., :4]  # x(6300,4) boxes
+        # conf = x[..., 4:5]  # x(6300,1) confidences
+        # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1))  # x(6300,1)  classes
+        # return tf.concat([conf, cls, xywh], 1)
+
+    @staticmethod
+    def _xywh2xyxy(xywh):
+        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+        x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
+        return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
+
+
+class AgnosticNMS(keras.layers.Layer):
+    # TF Agnostic NMS
+    def call(self, input, topk_all, iou_thres, conf_thres):
+        # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
+        return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
+                         fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
+                         name='agnostic_nms')
+
+    @staticmethod
+    def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25):  # agnostic NMS
+        boxes, classes, scores = x
+        class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
+        scores_inp = tf.reduce_max(scores, -1)
+        selected_inds = tf.image.non_max_suppression(
+            boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
+        selected_boxes = tf.gather(boxes, selected_inds)
+        padded_boxes = tf.pad(selected_boxes,
+                              paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
+                              mode="CONSTANT", constant_values=0.0)
+        selected_scores = tf.gather(scores_inp, selected_inds)
+        padded_scores = tf.pad(selected_scores,
+                               paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                               mode="CONSTANT", constant_values=-1.0)
+        selected_classes = tf.gather(class_inds, selected_inds)
+        padded_classes = tf.pad(selected_classes,
+                                paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+                                mode="CONSTANT", constant_values=-1.0)
+        valid_detections = tf.shape(selected_inds)[0]
+        return padded_boxes, padded_scores, padded_classes, valid_detections
+
+
+def representative_dataset_gen(dataset, ncalib=100):
+    # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
+    for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
+        input = np.transpose(img, [1, 2, 0])
+        input = np.expand_dims(input, axis=0).astype(np.float32)
+        input /= 255
+        yield [input]
+        if n >= ncalib:
+            break
+
+
+def run(weights=ROOT / 'yolov5s.pt',  # weights path
+        imgsz=(640, 640),  # inference size h,w
+        batch_size=1,  # batch size
+        dynamic=False,  # dynamic batch size
+        ):
+    # PyTorch model
+    im = torch.zeros((batch_size, 3, *imgsz))  # BCHW image
+    model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
+    _ = model(im)  # inference
+    model.info()
+
+    # TensorFlow model
+    im = tf.zeros((batch_size, *imgsz, 3))  # BHWC image
+    tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+    _ = tf_model.predict(im)  # inference
+
+    # Keras model
+    im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
+    keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
+    keras_model.summary()
+
+    LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
+
+
+def parse_opt():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='weights path')
+    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
+    opt = parser.parse_args()
+    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
+    print_args(FILE.stem, opt)
+    return opt
+
+
+def main(opt):
+    run(**vars(opt))
+
+
+if __name__ == "__main__":
+    opt = parse_opt()
+    main(opt)

yolov5/models/yolo.py

@@ -0,0 +1,329 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+YOLO-specific modules
+
+Usage:
+    $ python path/to/models/yolo.py --cfg yolov5s.yaml
+"""
+
+import argparse
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1]  # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+    sys.path.append(str(ROOT))  # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd())  # relative
+
+from models.common import *
+from models.experimental import *
+from utils.autoanchor import check_anchor_order
+from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
+from utils.plots import feature_visualization
+from utils.torch_utils import fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device, time_sync
+
+try:
+    import thop  # for FLOPs computation
+except ImportError:
+    thop = None
+
+
+class Detect(nn.Module):
+    stride = None  # strides computed during build
+    onnx_dynamic = False  # ONNX export parameter
+
+    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
+        super().__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        self.anchor_grid = [torch.zeros(1)] * self.nl  # init anchor grid
+        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        self.inplace = inplace  # use in-place ops (e.g. slice assignment)
+
+    def forward(self, x):
+        z = []  # inference output
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
+
+                y = x[i].sigmoid()
+                if self.inplace:
+                    y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
+                    xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                    y = torch.cat((xy, wh, y[..., 4:]), -1)
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    def _make_grid(self, nx=20, ny=20, i=0):
+        d = self.anchors[i].device
+        if check_version(torch.__version__, '1.10.0'):  # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
+            yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)], indexing='ij')
+        else:
+            yv, xv = torch.meshgrid([torch.arange(ny, device=d), torch.arange(nx, device=d)])
+        grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
+        anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
+            .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
+        return grid, anchor_grid
+
+
+class Model(nn.Module):
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super().__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg, encoding='ascii', errors='ignore') as f:
+                self.yaml = yaml.safe_load(f)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        self.inplace = self.yaml.get('inplace', True)
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            s = 256  # 2x min stride
+            m.inplace = self.inplace
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            m.anchors /= m.stride.view(-1, 1, 1)
+            check_anchor_order(m)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        LOGGER.info('')
+
+    def forward(self, x, augment=False, profile=False, visualize=False):
+        if augment:
+            return self._forward_augment(x)  # augmented inference, None
+        return self._forward_once(x, profile, visualize)  # single-scale inference, train
+
+    def _forward_augment(self, x):
+        img_size = x.shape[-2:]  # height, width
+        s = [1, 0.83, 0.67]  # scales
+        f = [None, 3, None]  # flips (2-ud, 3-lr)
+        y = []  # outputs
+        for si, fi in zip(s, f):
+            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+            yi = self._forward_once(xi)[0]  # forward
+            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+            yi = self._descale_pred(yi, fi, si, img_size)
+            y.append(yi)
+        y = self._clip_augmented(y)  # clip augmented tails
+        return torch.cat(y, 1), None  # augmented inference, train
+
+    def _forward_once(self, x, profile=False, visualize=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+            if profile:
+                self._profile_one_layer(m, x, dt)
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+            if visualize:
+                feature_visualization(x, m.type, m.i, save_dir=visualize)
+        return x
+
+    def _descale_pred(self, p, flips, scale, img_size):
+        # de-scale predictions following augmented inference (inverse operation)
+        if self.inplace:
+            p[..., :4] /= scale  # de-scale
+            if flips == 2:
+                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
+            elif flips == 3:
+                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
+        else:
+            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
+            if flips == 2:
+                y = img_size[0] - y  # de-flip ud
+            elif flips == 3:
+                x = img_size[1] - x  # de-flip lr
+            p = torch.cat((x, y, wh, p[..., 4:]), -1)
+        return p
+
+    def _clip_augmented(self, y):
+        # Clip YOLOv5 augmented inference tails
+        nl = self.model[-1].nl  # number of detection layers (P3-P5)
+        g = sum(4 ** x for x in range(nl))  # grid points
+        e = 1  # exclude layer count
+        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
+        y[0] = y[0][:, :-i]  # large
+        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
+        y[-1] = y[-1][:, i:]  # small
+        return y
+
+    def _profile_one_layer(self, m, x, dt):
+        c = isinstance(m, Detect)  # is final layer, copy input as inplace fix
+        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
+        t = time_sync()
+        for _ in range(10):
+            m(x.copy() if c else x)
+        dt.append((time_sync() - t) * 100)
+        if m == self.model[0]:
+            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  {'module'}")
+        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
+        if c:
+            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _print_biases(self):
+        m = self.model[-1]  # Detect() module
+        for mi in m.m:  # from
+            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
+            LOGGER.info(
+                ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+    # def _print_weights(self):
+    #     for m in self.model.modules():
+    #         if type(m) is Bottleneck:
+    #             LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        LOGGER.info('Fusing layers... ')
+        for m in self.model.modules():
+            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.forward_fuse  # update forward
+        self.info()
+        return self
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+    def _apply(self, fn):
+        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+        self = super()._apply(fn)
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            m.stride = fn(m.stride)
+            m.grid = list(map(fn, m.grid))
+            if isinstance(m.anchor_grid, list):
+                m.anchor_grid = list(map(fn, m.anchor_grid))
+        return self
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except NameError:
+                pass
+
+        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
+                 BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[x] for x in f)
+        elif m is Detect:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum(x.numel() for x in m_.parameters())  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--profile', action='store_true', help='profile model speed')
+    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
+    opt = parser.parse_args()
+    opt.cfg = check_yaml(opt.cfg)  # check YAML
+    print_args(FILE.stem, opt)
+    device = select_device(opt.device)
+
+    # Create model
+    model = Model(opt.cfg).to(device)
+    model.train()
+
+    # Profile
+    if opt.profile:
+        img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+        y = model(img, profile=True)
+
+    # Test all models
+    if opt.test:
+        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
+            try:
+                _ = Model(cfg)
+            except Exception as e:
+                print(f'Error in {cfg}: {e}')
+
+    # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
+    # from torch.utils.tensorboard import SummaryWriter
+    # tb_writer = SummaryWriter('.')
+    # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
+    # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), [])  # add model graph

yolov5/models/yolov5l.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5m.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5n.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5s.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/models/yolov5x.yaml

@@ -0,0 +1,48 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [64, 6, 2, 2]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 6, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 3, C3, [1024]],
+   [-1, 1, SPPF, [1024, 5]],  # 9
+  ]
+
+# YOLOv5 v6.0 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

yolov5/utils/__init__.py

@@ -0,0 +1,37 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+"""
+utils/initialization
+"""
+
+
+def notebook_init(verbose=True):
+    # Check system software and hardware
+    print('Checking setup...')
+
+    import os
+    import shutil
+
+    from utils.general import check_requirements, emojis, is_colab
+    from utils.torch_utils import select_device  # imports
+
+    check_requirements(('psutil', 'IPython'))
+    import psutil
+    from IPython import display  # to display images and clear console output
+
+    if is_colab():
+        shutil.rmtree('/content/sample_data', ignore_errors=True)  # remove colab /sample_data directory
+
+    if verbose:
+        # System info
+        # gb = 1 / 1000 ** 3  # bytes to GB
+        gib = 1 / 1024 ** 3  # bytes to GiB
+        ram = psutil.virtual_memory().total
+        total, used, free = shutil.disk_usage("/")
+        display.clear_output()
+        s = f'({os.cpu_count()} CPUs, {ram * gib:.1f} GB RAM, {(total - free) * gib:.1f}/{total * gib:.1f} GB disk)'
+    else:
+        s = ''
+
+    select_device(newline=False)
+    print(emojis(f'Setup complete ✅ {s}'))
+    return display