training prototype with notebook

README.md

@@ -1 +1,2 @@
 # Headshot Project
+

notebooks/.ipynb_checkpoints/detection_pytorch-checkpoint.ipynb

@@ -0,0 +1,192 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "13343cbd-bede-41d9-9506-08ed04e66cf6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Myo Win Zaw\\.conda\\envs\\ai_env\\lib\\site-packages\\torchvision\\io\\image.py:13: UserWarning: Failed to load image Python extension: '[WinError 127] The specified procedure could not be found'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?\n",
+      "  warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torch.utils.data import DataLoader, Dataset\n",
+    "from torchvision import transforms, datasets\n",
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "31812e9b-1b04-44fc-891e-1e77c866ff75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# declaration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "0c3b7de2-b89c-47f8-83d9-d20f27af390a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load image datas\n",
+    "\n",
+    "device = 'cpu'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "58383873-e2c3-4683-ba04-72bad7a6d773",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# dataset \n",
+    "class FaceDataset(Dataset):\n",
+    "    def __init__(self,data,labels,transforms=None):\n",
+    "        self.tranforms = tranforms\n",
+    "        self.data = x_data\n",
+    "        self.labels = y_labels\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.data)\n",
+    "\n",
+    "    def __getitem__(self, idx):\n",
+    "        # Load and preprocess the image at the given index\n",
+    "        image = self.data[idx]\n",
+    "        label = self.labels[idx]\n",
+    "        \n",
+    "        if self.transform:\n",
+    "            image = self.transform(image)\n",
+    "        return image,label"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "8d6e52a5-b80a-40fd-9a58-40255efba005",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Detector(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super().__init__()\n",
+    "        self.conv1 = nn.Conv2d(72,64,4)\n",
+    "\n",
+    "    def forward(self):\n",
+    "        pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "298e5cd7-d247-437d-ae69-271dbbdfdf03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# optimization\n",
+    "lr = 1e-3\n",
+    "# model = Detector().to(device)\n",
+    "# optimizer = torch.optim.Adam(model)\n",
+    "loss_fn = nn.CrossEntropyLoss()\n",
+    "\n",
+    "num_epochs = 50\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "89877e6b-9682-4d00-acae-94020722e7e1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "xi\n"
+     ]
+    },
+    {
+     "ename": "TypeError",
+     "evalue": "CrossEntropyLoss.forward() missing 2 required positional arguments: 'input' and 'target'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[43], line 9\u001b[0m\n\u001b[0;32m      6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m _ \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(dummy_dataset):\n\u001b[0;32m      7\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mxi\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m----> 9\u001b[0m     loss \u001b[38;5;241m=\u001b[39m \u001b[43mloss_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\.conda\\envs\\ai_env\\lib\\site-packages\\torch\\nn\\modules\\module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\ai_env\\lib\\site-packages\\torch\\nn\\modules\\module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "\u001b[1;31mTypeError\u001b[0m: CrossEntropyLoss.forward() missing 2 required positional arguments: 'input' and 'target'"
+     ]
+    }
+   ],
+   "source": [
+    "# train model\n",
+    "\n",
+    "dummy_dataset= ['hello']\n",
+    "\n",
+    "for i in range(num_epochs):\n",
+    "    for img,label in enumerate(dummy_dataset):\n",
+    "        optimizer.zero_grad()\n",
+    "        outputs = model(img,label)\n",
+    "        loss = loss_fn(outputs,labels)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "    print(f\"epoch {i} done\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a3e59e6-7701-4e11-8d29-c6e5468d63ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# eval model\n",
+    "def evaluate():\n",
+    "    pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0ddaf7e-185b-4190-b491-120008d1e1ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

notebooks/detection_pytorch.ipynb

@@ -0,0 +1,192 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "13343cbd-bede-41d9-9506-08ed04e66cf6",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "C:\\Users\\Myo Win Zaw\\.conda\\envs\\ai_env\\lib\\site-packages\\torchvision\\io\\image.py:13: UserWarning: Failed to load image Python extension: '[WinError 127] The specified procedure could not be found'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?\n",
+      "  warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torch.utils.data import DataLoader, Dataset\n",
+    "from torchvision import transforms, datasets\n",
+    "from tqdm import tqdm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "31812e9b-1b04-44fc-891e-1e77c866ff75",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# declaration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "0c3b7de2-b89c-47f8-83d9-d20f27af390a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load image datas\n",
+    "\n",
+    "device = 'cpu'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "58383873-e2c3-4683-ba04-72bad7a6d773",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# dataset \n",
+    "class FaceDataset(Dataset):\n",
+    "    def __init__(self,data,labels,transforms=None):\n",
+    "        self.tranforms = tranforms\n",
+    "        self.data = x_data\n",
+    "        self.labels = y_labels\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.data)\n",
+    "\n",
+    "    def __getitem__(self, idx):\n",
+    "        # Load and preprocess the image at the given index\n",
+    "        image = self.data[idx]\n",
+    "        label = self.labels[idx]\n",
+    "        \n",
+    "        if self.transform:\n",
+    "            image = self.transform(image)\n",
+    "        return image,label"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "8d6e52a5-b80a-40fd-9a58-40255efba005",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class Detector(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super().__init__()\n",
+    "        self.conv1 = nn.Conv2d(72,64,4)\n",
+    "\n",
+    "    def forward(self):\n",
+    "        pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "298e5cd7-d247-437d-ae69-271dbbdfdf03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# optimization\n",
+    "lr = 1e-3\n",
+    "# model = Detector().to(device)\n",
+    "# optimizer = torch.optim.Adam(model)\n",
+    "loss_fn = nn.CrossEntropyLoss()\n",
+    "\n",
+    "num_epochs = 50\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "89877e6b-9682-4d00-acae-94020722e7e1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "xi\n"
+     ]
+    },
+    {
+     "ename": "TypeError",
+     "evalue": "CrossEntropyLoss.forward() missing 2 required positional arguments: 'input' and 'target'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn[43], line 9\u001b[0m\n\u001b[0;32m      6\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m _ \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(dummy_dataset):\n\u001b[0;32m      7\u001b[0m     \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mxi\u001b[39m\u001b[38;5;124m'\u001b[39m)\n\u001b[1;32m----> 9\u001b[0m     loss \u001b[38;5;241m=\u001b[39m \u001b[43mloss_fn\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[1;32m~\\.conda\\envs\\ai_env\\lib\\site-packages\\torch\\nn\\modules\\module.py:1511\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1509\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1510\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1511\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32m~\\.conda\\envs\\ai_env\\lib\\site-packages\\torch\\nn\\modules\\module.py:1520\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1515\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1516\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1517\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1518\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1519\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1520\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m forward_call(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m   1522\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1523\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "\u001b[1;31mTypeError\u001b[0m: CrossEntropyLoss.forward() missing 2 required positional arguments: 'input' and 'target'"
+     ]
+    }
+   ],
+   "source": [
+    "# train model\n",
+    "\n",
+    "dummy_dataset= ['hello']\n",
+    "\n",
+    "for i in range(num_epochs):\n",
+    "    for img,label in enumerate(dummy_dataset):\n",
+    "        optimizer.zero_grad()\n",
+    "        outputs = model(img,label)\n",
+    "        loss = loss_fn(outputs,labels)\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "    print(f\"epoch {i} done\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7a3e59e6-7701-4e11-8d29-c6e5468d63ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# eval model\n",
+    "def evaluate():\n",
+    "    pass"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0ddaf7e-185b-4190-b491-120008d1e1ea",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}