Getting the correct data out.

.gitignore

@@ -1,4 +1,5 @@
 bin
 lib
 output
-share
+share
+input_img.jpg

=1.12

@@ -1,14 +1,14 @@
 Requirement already satisfied: xtcocotools in ./lib/python3.10/site-packages (1.14.3)
-Requirement already satisfied: cython>=0.27.3 in ./lib/python3.10/site-packages (from xtcocotools) (3.0.7)
-Requirement already satisfied: numpy>=1.20.0 in ./lib/python3.10/site-packages (from xtcocotools) (1.23.0)
 Requirement already satisfied: matplotlib>=2.1.0 in ./lib/python3.10/site-packages (from xtcocotools) (3.7.4)
 Requirement already satisfied: setuptools>=18.0 in ./lib/python3.10/site-packages (from xtcocotools) (65.5.0)
+Requirement already satisfied: cython>=0.27.3 in ./lib/python3.10/site-packages (from xtcocotools) (3.0.7)
+Requirement already satisfied: numpy>=1.20.0 in ./lib/python3.10/site-packages (from xtcocotools) (1.23.0)
+Requirement already satisfied: fonttools>=4.22.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (4.47.0)
+Requirement already satisfied: python-dateutil>=2.7 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.8.2)
+Requirement already satisfied: packaging>=20.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (23.2)
 Requirement already satisfied: kiwisolver>=1.0.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.4.5)
 Requirement already satisfied: cycler>=0.10 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (0.12.1)
+Requirement already satisfied: pyparsing>=2.3.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.4.5)
 Requirement already satisfied: contourpy>=1.0.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (1.2.0)
 Requirement already satisfied: pillow>=6.2.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (9.4.0)
-Requirement already satisfied: packaging>=20.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (23.2)
-Requirement already satisfied: fonttools>=4.22.0 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (4.47.0)
-Requirement already satisfied: python-dateutil>=2.7 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.8.2)
-Requirement already satisfied: pyparsing>=2.3.1 in ./lib/python3.10/site-packages (from matplotlib>=2.1.0->xtcocotools) (2.4.5)
 Requirement already satisfied: six>=1.5 in ./lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib>=2.1.0->xtcocotools) (1.16.0)

app.py

@@ -9,63 +9,73 @@ os.system("pip install 'mmpose'")
 
 import PIL
 import cv2
-import mmpose
 import numpy as np
 
 import torch
 from mmpose.apis import MMPoseInferencer
+from mmpose.apis import inference_topdown, init_model
+from mmpose.utils import register_all_modules
+register_all_modules()
+
 import gradio as gr
 
 import warnings
 
 warnings.filterwarnings("ignore")
 
-mmpose_model_list = ["human", "hand", "face", "animal", "wholebody",
-                     "vitpose", "vitpose-s", "vitpose-b", "vitpose-l", "vitpose-h"]
-
 def save_image(img, img_path):
     # Convert PIL image to OpenCV image
     img = cv2.cvtColor(np.array(img), cv2.COLOR_RGB2BGR)
     # Save OpenCV image
     cv2.imwrite(img_path, img)
 
-# def download_test_image():
-#     # Images
-#     torch.hub.download_url_to_file(
-#         'https://user-images.githubusercontent.com/59380685/266264420-21575a83-4057-41cf-8a4a-b3ea6f332d79.jpg',
-#         'bus.jpg')
-#     torch.hub.download_url_to_file(
-#         'https://user-images.githubusercontent.com/59380685/266264536-82afdf58-6b9a-4568-b9df-551ee72cb6d9.jpg',
-#         'dogs.jpg')
-#     torch.hub.download_url_to_file(
-#         'https://user-images.githubusercontent.com/59380685/266264600-9d0c26ca-8ba6-45f2-b53b-4dc98460c43e.jpg',
-#         'zidane.jpg')
-
-
-def predict_pose(img, model_name):
+def predict_pose(img):
     img_path = "input_img.jpg"
-    out_dir = "./output";
     save_image(img, img_path)
+
+    result = mmpose_coco(img_path)
+    keypoints = result[0].pred_instances['keypoints'][0]
+
+    # Create a dictionary to store keypoints and their names
+    keypoints_data = {
+        'keypoints': keypoints.tolist(),
+        'keypoint_names': [
+            'nose',
+            'left_eye',
+            'right_eye',
+            'left_ear',
+            'right_ear',
+            'left_shoulder',
+            'right_shoulder',
+            'left_elbow',
+            'right_elbow',
+            'left_wrist',
+            'right_wrist',
+            'left_hip',
+            'right_hip',
+            'left_knee',
+            'right_knee',
+            'left_ankle',
+            'right_ankle'
+        ]
+    }
+    return (img, keypoints_data)
+
+def mmpose_coco(img_path, 
+                config_file = 'mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py', 
+                checkpoint_file = 'mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192-0e67c616_20220913.pth'):
     device = torch.cuda.current_device() if torch.cuda.is_available() else 'cpu'
-    inferencer = MMPoseInferencer(model_name, device=device)
-    result_generator = inferencer(img_path, show=False, out_dir=out_dir)
-    result = next(result_generator)
-    print(result)
-    save_dir = './output/visualizations/'
-    if os.path.exists(save_dir):
-        out_img_path = save_dir + img_path
-        print("out_img_path: ", out_img_path)
-    else:
-        out_img_path = img_path
-    out_img = PIL.Image.open(out_img_path)
-    return (out_img, result)
+    # coco keypoints: 
+    # https://github.com/open-mmlab/mmpose/blob/master/mmpose/datasets/datasets/top_down/topdown_coco_dataset.py#L28
+    model = init_model(config_file, checkpoint_file, device=device)
+    results = inference_topdown(model, img_path)
+    return results
 
 # download_test_image()
 input_image = gr.inputs.Image(type='pil', label="Original Image")
-model_name = gr.inputs.Dropdown(choices=[m for m in mmpose_model_list], label='Model')
 output_image = gr.outputs.Image(type="pil", label="Output Image")
 output_text = gr.outputs.Textbox(label="Output Text")
 
 title = "MMPose detection for ShopByShape"
-iface = gr.Interface(fn=predict_pose, inputs=[input_image, model_name], outputs=[output_image, output_text], title=title)
+iface = gr.Interface(fn=predict_pose, inputs=[input_image], outputs=[output_image, output_text], title=title)
 iface.launch()

mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192-0e67c616_20220913.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e67c6167d6a10fe8f27e3da1e9a415b57289d5820dcca2b42bd8079df4b7a3a
+size 269176125

mmpose/td-hm_hrnet-w48_8xb32-210e_coco-256x192.py

@@ -0,0 +1,286 @@
+auto_scale_lr = dict(base_batch_size=512)
+backend_args = dict(backend='local')
+codec = dict(
+    heatmap_size=(
+        48,
+        64,
+    ),
+    input_size=(
+        192,
+        256,
+    ),
+    sigma=2,
+    type='MSRAHeatmap')
+custom_hooks = [
+    dict(type='SyncBuffersHook'),
+]
+data_mode = 'topdown'
+data_root = 'data/coco/'
+dataset_type = 'CocoDataset'
+default_hooks = dict(
+    badcase=dict(
+        badcase_thr=5,
+        enable=False,
+        metric_type='loss',
+        out_dir='badcase',
+        type='BadCaseAnalysisHook'),
+    checkpoint=dict(
+        interval=10,
+        rule='greater',
+        save_best='coco/AP',
+        type='CheckpointHook'),
+    logger=dict(interval=50, type='LoggerHook'),
+    param_scheduler=dict(type='ParamSchedulerHook'),
+    sampler_seed=dict(type='DistSamplerSeedHook'),
+    timer=dict(type='IterTimerHook'),
+    visualization=dict(enable=False, type='PoseVisualizationHook'))
+default_scope = 'mmpose'
+env_cfg = dict(
+    cudnn_benchmark=False,
+    dist_cfg=dict(backend='nccl'),
+    mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0))
+load_from = None
+log_level = 'INFO'
+log_processor = dict(
+    by_epoch=True, num_digits=6, type='LogProcessor', window_size=50)
+model = dict(
+    backbone=dict(
+        extra=dict(
+            stage1=dict(
+                block='BOTTLENECK',
+                num_blocks=(4, ),
+                num_branches=1,
+                num_channels=(64, ),
+                num_modules=1),
+            stage2=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                ),
+                num_branches=2,
+                num_channels=(
+                    48,
+                    96,
+                ),
+                num_modules=1),
+            stage3=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=3,
+                num_channels=(
+                    48,
+                    96,
+                    192,
+                ),
+                num_modules=4),
+            stage4=dict(
+                block='BASIC',
+                num_blocks=(
+                    4,
+                    4,
+                    4,
+                    4,
+                ),
+                num_branches=4,
+                num_channels=(
+                    48,
+                    96,
+                    192,
+                    384,
+                ),
+                num_modules=3)),
+        in_channels=3,
+        init_cfg=dict(
+            checkpoint=
+            'https://download.openmmlab.com/mmpose/pretrain_models/hrnet_w48-8ef0771d.pth',
+            type='Pretrained'),
+        type='HRNet'),
+    data_preprocessor=dict(
+        bgr_to_rgb=True,
+        mean=[
+            123.675,
+            116.28,
+            103.53,
+        ],
+        std=[
+            58.395,
+            57.12,
+            57.375,
+        ],
+        type='PoseDataPreprocessor'),
+    head=dict(
+        decoder=dict(
+            heatmap_size=(
+                48,
+                64,
+            ),
+            input_size=(
+                192,
+                256,
+            ),
+            sigma=2,
+            type='MSRAHeatmap'),
+        deconv_out_channels=None,
+        in_channels=48,
+        loss=dict(type='KeypointMSELoss', use_target_weight=True),
+        out_channels=17,
+        type='HeatmapHead'),
+    test_cfg=dict(flip_mode='heatmap', flip_test=True, shift_heatmap=True),
+    type='TopdownPoseEstimator')
+optim_wrapper = dict(optimizer=dict(lr=0.0005, type='Adam'))
+param_scheduler = [
+    dict(
+        begin=0, by_epoch=False, end=500, start_factor=0.001, type='LinearLR'),
+    dict(
+        begin=0,
+        by_epoch=True,
+        end=210,
+        gamma=0.1,
+        milestones=[
+            170,
+            200,
+        ],
+        type='MultiStepLR'),
+]
+resume = False
+test_cfg = dict()
+test_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        ann_file='annotations/person_keypoints_val2017.json',
+        bbox_file=
+        'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json',
+        data_mode='topdown',
+        data_prefix=dict(img='val2017/'),
+        data_root='data/coco/',
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(input_size=(
+                192,
+                256,
+            ), type='TopdownAffine'),
+            dict(type='PackPoseInputs'),
+        ],
+        test_mode=True,
+        type='CocoDataset'),
+    drop_last=False,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(round_up=False, shuffle=False, type='DefaultSampler'))
+test_evaluator = dict(
+    ann_file='data/coco/annotations/person_keypoints_val2017.json',
+    type='CocoMetric')
+train_cfg = dict(by_epoch=True, max_epochs=210, val_interval=10)
+train_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        ann_file='annotations/person_keypoints_train2017.json',
+        data_mode='topdown',
+        data_prefix=dict(img='train2017/'),
+        data_root='data/coco/',
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(direction='horizontal', type='RandomFlip'),
+            dict(type='RandomHalfBody'),
+            dict(type='RandomBBoxTransform'),
+            dict(input_size=(
+                192,
+                256,
+            ), type='TopdownAffine'),
+            dict(
+                encoder=dict(
+                    heatmap_size=(
+                        48,
+                        64,
+                    ),
+                    input_size=(
+                        192,
+                        256,
+                    ),
+                    sigma=2,
+                    type='MSRAHeatmap'),
+                type='GenerateTarget'),
+            dict(type='PackPoseInputs'),
+        ],
+        type='CocoDataset'),
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(shuffle=True, type='DefaultSampler'))
+train_pipeline = [
+    dict(type='LoadImage'),
+    dict(type='GetBBoxCenterScale'),
+    dict(direction='horizontal', type='RandomFlip'),
+    dict(type='RandomHalfBody'),
+    dict(type='RandomBBoxTransform'),
+    dict(input_size=(
+        192,
+        256,
+    ), type='TopdownAffine'),
+    dict(
+        encoder=dict(
+            heatmap_size=(
+                48,
+                64,
+            ),
+            input_size=(
+                192,
+                256,
+            ),
+            sigma=2,
+            type='MSRAHeatmap'),
+        type='GenerateTarget'),
+    dict(type='PackPoseInputs'),
+]
+val_cfg = dict()
+val_dataloader = dict(
+    batch_size=32,
+    dataset=dict(
+        ann_file='annotations/person_keypoints_val2017.json',
+        bbox_file=
+        'data/coco/person_detection_results/COCO_val2017_detections_AP_H_56_person.json',
+        data_mode='topdown',
+        data_prefix=dict(img='val2017/'),
+        data_root='data/coco/',
+        pipeline=[
+            dict(type='LoadImage'),
+            dict(type='GetBBoxCenterScale'),
+            dict(input_size=(
+                192,
+                256,
+            ), type='TopdownAffine'),
+            dict(type='PackPoseInputs'),
+        ],
+        test_mode=True,
+        type='CocoDataset'),
+    drop_last=False,
+    num_workers=2,
+    persistent_workers=True,
+    sampler=dict(round_up=False, shuffle=False, type='DefaultSampler'))
+val_evaluator = dict(
+    ann_file='data/coco/annotations/person_keypoints_val2017.json',
+    type='CocoMetric')
+val_pipeline = [
+    dict(type='LoadImage'),
+    dict(type='GetBBoxCenterScale'),
+    dict(input_size=(
+        192,
+        256,
+    ), type='TopdownAffine'),
+    dict(type='PackPoseInputs'),
+]
+vis_backends = [
+    dict(type='LocalVisBackend'),
+]
+visualizer = dict(
+    name='visualizer',
+    type='PoseLocalVisualizer',
+    vis_backends=[
+        dict(type='LocalVisBackend'),
+    ])