maybe good?
This commit is contained in:
@@ -314,94 +314,163 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 224,
|
||||
"execution_count": 65,
|
||||
"id": "a44b7aa4",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-04-27T15:21:54.599035Z",
|
||||
"start_time": "2024-04-27T15:21:54.587252Z"
|
||||
"end_time": "2024-04-28T07:13:16.866724Z",
|
||||
"start_time": "2024-04-28T07:13:16.841471Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from torch.utils.data import TensorDataset, DataLoader\n",
|
||||
"import torch\n",
|
||||
"from torch import nn\n",
|
||||
"class tinyCNN(nn.Module):\n",
|
||||
" def __init__(self, num_classes):\n",
|
||||
" super(tinyCNN, self).__init__()\n",
|
||||
"\n",
|
||||
"class Model: \n",
|
||||
" \"\"\"\n",
|
||||
" This class represents an AI model.\n",
|
||||
" \"\"\"\n",
|
||||
" self.conv1 = nn.Conv2d(1,32,3,stride=1,padding=0)\n",
|
||||
" self.conv2 = nn.Conv2d(32,32,3,stride=1,padding=0)\n",
|
||||
" self.conv3 = nn.Conv2d(32,64,3,stride=1,padding=0)\n",
|
||||
" self.conv4 = nn.Conv2d(64,64,3,stride=1,padding=0)\n",
|
||||
" \n",
|
||||
" self.relu = nn.ReLU()\n",
|
||||
" self.maxpool = nn.MaxPool2d(2)\n",
|
||||
" self.batchnorm1 = nn.BatchNorm2d(32)\n",
|
||||
" self.batchnorm2 = nn.BatchNorm2d(64)\n",
|
||||
" self.fc = nn.Linear(64, num_classes)\n",
|
||||
" self.flatten = nn.Flatten()\n",
|
||||
"\n",
|
||||
" def forward(self, x):\n",
|
||||
" x = self.conv1(x)\n",
|
||||
" x = self.relu(x)\n",
|
||||
" \n",
|
||||
" x = self.batchnorm1(x)\n",
|
||||
" x = self.maxpool(x)\n",
|
||||
" \n",
|
||||
" x = self.conv2(x)\n",
|
||||
" x = self.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.conv3(x)\n",
|
||||
" x = self.relu(x)\n",
|
||||
"\n",
|
||||
" x = self.batchnorm2(x)\n",
|
||||
" x = self.maxpool(x)\n",
|
||||
" x = self.flatten(x)\n",
|
||||
" x = self.fc(x)\n",
|
||||
" return x\n",
|
||||
" \n",
|
||||
" def __init__(self):\n",
|
||||
"class CIFARCNN(nn.Module):\n",
|
||||
" def __init__(self, classes):\n",
|
||||
" super().__init__()\n",
|
||||
" \"\"\"\n",
|
||||
" Constructor for Model class.\n",
|
||||
" \n",
|
||||
" Parameters\n",
|
||||
" ----------\n",
|
||||
" self : object\n",
|
||||
" The instance of the object passed by Python.\n",
|
||||
" classes: integer that corresponds to the number of classes for CIFAR-10\n",
|
||||
" \"\"\"\n",
|
||||
" # TODO: Replace the following code with your own initialization code.\n",
|
||||
" self.model = nn.Sequential(\n",
|
||||
" nn.LSTM(256, 128, 2, batch_first=True),\n",
|
||||
" nn.Linear(128, 6),\n",
|
||||
" self.flatten = nn.Flatten()\n",
|
||||
" self.conv = nn.Sequential(\n",
|
||||
" nn.Conv2d(1, 32, 3),\n",
|
||||
" nn.MaxPool2d(2),\n",
|
||||
" nn.LeakyReLU(0.1),\n",
|
||||
" nn.Conv2d(32, 64, (3, 3)),\n",
|
||||
" nn.MaxPool2d(2),\n",
|
||||
" nn.LeakyReLU(0.1),\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" self.fc = nn.Sequential(\n",
|
||||
" nn.Linear(256, 256),\n",
|
||||
" nn.LeakyReLU(0.1),\n",
|
||||
" nn.Linear(256, 128),\n",
|
||||
" nn.LeakyReLU(0.1),\n",
|
||||
" nn.Linear(128, classes)\n",
|
||||
" )\n",
|
||||
" \n",
|
||||
" def process(self, X):\n",
|
||||
" X_array = np.zeros((10, 16, 16))\n",
|
||||
" for i, video in enumerate(X):\n",
|
||||
" X_array[i, :, :] = video\n",
|
||||
" X_array = X_array.reshape((10, 1, 256))\n",
|
||||
" print(X_array.shape)\n",
|
||||
" \n",
|
||||
" return torch.from_numpy(X_array).float()\n",
|
||||
" def forward(self, x):\n",
|
||||
" # YOUR CODE HERE\n",
|
||||
" x = self.conv(x)\n",
|
||||
" x = self.flatten(x)\n",
|
||||
" x = self.fc(x)\n",
|
||||
" return x\n",
|
||||
"\n",
|
||||
"# video is a numpy array of shape (L, H, W)\n",
|
||||
"def clean_batch(batch):\n",
|
||||
" batch = np.array(batch)\n",
|
||||
" temp_x = batch.reshape(-1, 256)\n",
|
||||
" np.nan_to_num(temp_x, copy=False)\n",
|
||||
" col_mean = np.nanmean(temp_x, axis=0)\n",
|
||||
" inds = np.where(np.isnan(temp_x))\n",
|
||||
" temp_x[inds] = np.take(col_mean, inds[1])\n",
|
||||
" temp_x = np.clip(temp_x, 1, 255)\n",
|
||||
" batch = temp_x.reshape(-1, 1, 16,16)\n",
|
||||
" return torch.tensor(batch, dtype=torch.float32)\n",
|
||||
"def flatten_data(X, y):\n",
|
||||
" not_nan_indices = np.argwhere(~np.isnan(np.array(y))).squeeze()\n",
|
||||
" # Remove non y columns\n",
|
||||
" y = [y[i] for i in not_nan_indices]\n",
|
||||
" X = [X[i] for i in not_nan_indices]\n",
|
||||
" flattened_x = [video[i] for video in X for i in range(video.shape[0])]\n",
|
||||
" flattened_y = np.repeat(y, [video.shape[0] for video in X])\n",
|
||||
" flattened_x = clean_batch(flattened_x)\n",
|
||||
" return flattened_x, torch.Tensor(np.array(flattened_y, dtype=np.int64)).long()\n",
|
||||
"\n",
|
||||
"def train(model, criterion, optimizer, loader, epochs = 10):\n",
|
||||
" for epoch in range(epochs):\n",
|
||||
" for idx, (inputs, labels) in enumerate(loader):\n",
|
||||
" optimizer.zero_grad()\n",
|
||||
" outputs = model(inputs)\n",
|
||||
" loss = criterion(outputs, labels)\n",
|
||||
" loss.backward()\n",
|
||||
" optimizer.step()\n",
|
||||
" print(f'Epoch {epoch}, Loss: {loss.item()}')\n",
|
||||
" return model\n",
|
||||
"def process_data(X, y):\n",
|
||||
" y = np.array(y)\n",
|
||||
" X = np.array([video[:6] for video in X])\n",
|
||||
" tensor_videos = torch.tensor(X, dtype=torch.float32)\n",
|
||||
" # Clip values to 0 and 255\n",
|
||||
" tensor_videos = np.clip(tensor_videos, 0, 255)\n",
|
||||
" # Replace NaNs in each frame, with the average of the frame. This was generated with GPT\n",
|
||||
" for i in range(tensor_videos.shape[0]):\n",
|
||||
" for j in range(tensor_videos.shape[1]):\n",
|
||||
" tensor_videos[i][j][torch.isnan(tensor_videos[i][j])] = torch.mean(tensor_videos[i][j][~torch.isnan(tensor_videos[i][j])])\n",
|
||||
" \n",
|
||||
" # Undersample the data for each of the 6 classes. Select max of 300 samples for each class\n",
|
||||
" # Very much generated with the assitance of chatGPT with some modifications\n",
|
||||
" # Get the indices of each class\n",
|
||||
" indices = [np.argwhere(y == i).squeeze(1) for i in range(6)]\n",
|
||||
" # Get the number of samples to take for each class\n",
|
||||
" num_samples_to_take = 300\n",
|
||||
" # Get the indices of the samples to take\n",
|
||||
" indices_to_take = [np.random.choice(indices[i], num_samples_to_take, replace=True) for i in range(6)]\n",
|
||||
" # Concatenate the indices\n",
|
||||
" indices_to_take = np.concatenate(indices_to_take)\n",
|
||||
" # Select the samples\n",
|
||||
" tensor_videos = tensor_videos[indices_to_take]\n",
|
||||
" y = y[indices_to_take]\n",
|
||||
" return torch.Tensor(tensor_videos), torch.Tensor(y)\n",
|
||||
"\n",
|
||||
"class Model():\n",
|
||||
" def __init__(self):\n",
|
||||
" self.cnn = CIFARCNN(6)\n",
|
||||
" def fit(self, X, y):\n",
|
||||
" \"\"\"\n",
|
||||
" Train the model using the input data.\n",
|
||||
" \n",
|
||||
" Parameters\n",
|
||||
" ----------\n",
|
||||
" X : list of size (n_samples)\n",
|
||||
" Each item in the list is a grayscale video of shape (L, H, W).\n",
|
||||
" L represents the length of the video, which may vary between videos. \n",
|
||||
" H and W represent the height and width, which are consistent across all videos. \n",
|
||||
" y : list of size (n_samples)\n",
|
||||
" Class labels for videos\n",
|
||||
" \n",
|
||||
" Returns\n",
|
||||
" -------\n",
|
||||
" self : object\n",
|
||||
" Returns an instance of the trained model.\n",
|
||||
" \"\"\"\n",
|
||||
" X = self.process(X)\n",
|
||||
" train_dataset = TensorDataset(X, torch.tensor(y))\n",
|
||||
" train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
|
||||
"\n",
|
||||
" self.cnn.train()\n",
|
||||
" X, y = process_data(X, y)\n",
|
||||
" print(X.shape, y.shape)\n",
|
||||
" train_dataset = torch.utils.data.TensorDataset(X, y)\n",
|
||||
" train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
|
||||
" criterion = nn.CrossEntropyLoss()\n",
|
||||
" optimizer = torch.optim.Adam(self.cnn.parameters(), lr=0.001)\n",
|
||||
" self.model = train(self.cnn, criterion, optimizer, train_loader)\n",
|
||||
" return self\n",
|
||||
" \n",
|
||||
" def predict(self, X):\n",
|
||||
" \"\"\"\n",
|
||||
" Use the trained model to make predictions.\n",
|
||||
" \n",
|
||||
" Parameters\n",
|
||||
" ----------\n",
|
||||
" X : list of size (n_samples)\n",
|
||||
" Each item in the list is a grayscale video of shape (L, H, W).\n",
|
||||
" L represents the length of the video, which may vary between videos. \n",
|
||||
" H and W represent the height and width, which are consistent across all videos. \n",
|
||||
" \n",
|
||||
" Returns\n",
|
||||
" -------\n",
|
||||
" ndarray of shape (n_samples,)\n",
|
||||
" Predicted target values per element in X.\n",
|
||||
" \n",
|
||||
" \"\"\"\n",
|
||||
" result = []\n",
|
||||
" for video in X:\n",
|
||||
" result.append(self.model(self.process(video)).argmax(dim=1).detach().numpy())\n",
|
||||
" return result"
|
||||
" self.cnn.eval()\n",
|
||||
" results = []\n",
|
||||
" for idx, batch in enumerate(X):\n",
|
||||
" batch = clean_batch(batch)\n",
|
||||
" pred = self.cnn(batch)\n",
|
||||
" result = torch.argmax(pred, axis=1)\n",
|
||||
" results.append(torch.max(result))\n",
|
||||
" return results\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -416,12 +485,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 49,
|
||||
"id": "4f4dd489",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-04-27T13:36:15.463930Z",
|
||||
"start_time": "2024-04-27T13:36:15.298430Z"
|
||||
"end_time": "2024-04-28T07:10:17.037378Z",
|
||||
"start_time": "2024-04-28T07:10:17.031404Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
@@ -436,12 +505,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 50,
|
||||
"id": "3064e0ff",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-04-27T13:36:18.535709Z",
|
||||
"start_time": "2024-04-27T13:36:18.509684Z"
|
||||
"end_time": "2024-04-28T07:10:18.316631Z",
|
||||
"start_time": "2024-04-28T07:10:18.289375Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
@@ -455,12 +524,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 225,
|
||||
"execution_count": 67,
|
||||
"id": "27c9fd10",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2024-04-27T15:21:56.847320Z",
|
||||
"start_time": "2024-04-27T15:21:56.787331Z"
|
||||
"end_time": "2024-04-28T07:14:48.901477Z",
|
||||
"start_time": "2024-04-28T07:14:48.343775Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
@@ -468,31 +537,37 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"(10, 1, 256)\n"
|
||||
"torch.Size([1800, 6, 16, 16]) torch.Size([1800])\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"ename": "TypeError",
|
||||
"evalue": "linear(): argument 'input' (position 1) must be Tensor, not tuple",
|
||||
"ename": "RuntimeError",
|
||||
"evalue": "Given groups=1, weight of size [32, 1, 3, 3], expected input[32, 6, 16, 16] to have 1 channels, but got 6 channels instead",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001B[0;31m---------------------------------------------------------------------------\u001B[0m",
|
||||
"\u001B[0;31mTypeError\u001B[0m Traceback (most recent call last)",
|
||||
"Cell \u001B[0;32mIn[225], line 13\u001B[0m\n\u001B[1;32m 11\u001B[0m model \u001B[38;5;241m=\u001B[39m Model()\n\u001B[1;32m 12\u001B[0m \u001B[38;5;66;03m# model.fit(X_train, y_train)\u001B[39;00m\n\u001B[0;32m---> 13\u001B[0m y_pred \u001B[38;5;241m=\u001B[39m \u001B[43mmodel\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mpredict\u001B[49m\u001B[43m(\u001B[49m\u001B[43mX_test\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 14\u001B[0m \u001B[38;5;28mprint\u001B[39m(y_pred[\u001B[38;5;241m0\u001B[39m])\n\u001B[1;32m 15\u001B[0m \u001B[38;5;28mprint\u001B[39m(y[\u001B[38;5;241m0\u001B[39m])\n",
|
||||
"Cell \u001B[0;32mIn[224], line 77\u001B[0m, in \u001B[0;36mModel.predict\u001B[0;34m(self, X)\u001B[0m\n\u001B[1;32m 75\u001B[0m result \u001B[38;5;241m=\u001B[39m []\n\u001B[1;32m 76\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m video \u001B[38;5;129;01min\u001B[39;00m X:\n\u001B[0;32m---> 77\u001B[0m result\u001B[38;5;241m.\u001B[39mappend(\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mmodel\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mprocess\u001B[49m\u001B[43m(\u001B[49m\u001B[43mvideo\u001B[49m\u001B[43m)\u001B[49m\u001B[43m)\u001B[49m\u001B[38;5;241m.\u001B[39margmax(dim\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m1\u001B[39m)\u001B[38;5;241m.\u001B[39mdetach()\u001B[38;5;241m.\u001B[39mnumpy())\n\u001B[1;32m 78\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m result\n",
|
||||
"\u001B[0;31mRuntimeError\u001B[0m Traceback (most recent call last)",
|
||||
"File \u001B[0;32m<timed exec>:12\u001B[0m\n",
|
||||
"Cell \u001B[0;32mIn[65], line 137\u001B[0m, in \u001B[0;36mModel.fit\u001B[0;34m(self, X, y)\u001B[0m\n\u001B[1;32m 135\u001B[0m criterion \u001B[38;5;241m=\u001B[39m nn\u001B[38;5;241m.\u001B[39mCrossEntropyLoss()\n\u001B[1;32m 136\u001B[0m optimizer \u001B[38;5;241m=\u001B[39m torch\u001B[38;5;241m.\u001B[39moptim\u001B[38;5;241m.\u001B[39mAdam(\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mcnn\u001B[38;5;241m.\u001B[39mparameters(), lr\u001B[38;5;241m=\u001B[39m\u001B[38;5;241m0.001\u001B[39m)\n\u001B[0;32m--> 137\u001B[0m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mmodel \u001B[38;5;241m=\u001B[39m \u001B[43mtrain\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mcnn\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mcriterion\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43moptimizer\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mtrain_loader\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 138\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28mself\u001B[39m\n",
|
||||
"Cell \u001B[0;32mIn[65], line 94\u001B[0m, in \u001B[0;36mtrain\u001B[0;34m(model, criterion, optimizer, loader, epochs)\u001B[0m\n\u001B[1;32m 92\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m idx, (inputs, labels) \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28menumerate\u001B[39m(loader):\n\u001B[1;32m 93\u001B[0m optimizer\u001B[38;5;241m.\u001B[39mzero_grad()\n\u001B[0;32m---> 94\u001B[0m outputs \u001B[38;5;241m=\u001B[39m \u001B[43mmodel\u001B[49m\u001B[43m(\u001B[49m\u001B[43minputs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 95\u001B[0m loss \u001B[38;5;241m=\u001B[39m criterion(outputs, labels)\n\u001B[1;32m 96\u001B[0m loss\u001B[38;5;241m.\u001B[39mbackward()\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001B[0m, in \u001B[0;36mModule._wrapped_call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1510\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1511\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call_impl\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001B[0m, in \u001B[0;36mModule._call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1516\u001B[0m \u001B[38;5;66;03m# this function, and just call forward.\u001B[39;00m\n\u001B[1;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[1;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[1;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[0;32m-> 1520\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mforward_call\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 1522\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m 1523\u001B[0m result \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n",
|
||||
"Cell \u001B[0;32mIn[65], line 64\u001B[0m, in \u001B[0;36mCIFARCNN.forward\u001B[0;34m(self, x)\u001B[0m\n\u001B[1;32m 62\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mforward\u001B[39m(\u001B[38;5;28mself\u001B[39m, x):\n\u001B[1;32m 63\u001B[0m \u001B[38;5;66;03m# YOUR CODE HERE\u001B[39;00m\n\u001B[0;32m---> 64\u001B[0m x \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconv\u001B[49m\u001B[43m(\u001B[49m\u001B[43mx\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 65\u001B[0m x \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mflatten(x)\n\u001B[1;32m 66\u001B[0m x \u001B[38;5;241m=\u001B[39m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mfc(x)\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001B[0m, in \u001B[0;36mModule._wrapped_call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1510\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1511\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call_impl\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001B[0m, in \u001B[0;36mModule._call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1516\u001B[0m \u001B[38;5;66;03m# this function, and just call forward.\u001B[39;00m\n\u001B[1;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[1;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[1;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[0;32m-> 1520\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mforward_call\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 1522\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m 1523\u001B[0m result \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/container.py:217\u001B[0m, in \u001B[0;36mSequential.forward\u001B[0;34m(self, input)\u001B[0m\n\u001B[1;32m 215\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mforward\u001B[39m(\u001B[38;5;28mself\u001B[39m, \u001B[38;5;28minput\u001B[39m):\n\u001B[1;32m 216\u001B[0m \u001B[38;5;28;01mfor\u001B[39;00m module \u001B[38;5;129;01min\u001B[39;00m \u001B[38;5;28mself\u001B[39m:\n\u001B[0;32m--> 217\u001B[0m \u001B[38;5;28minput\u001B[39m \u001B[38;5;241m=\u001B[39m \u001B[43mmodule\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43minput\u001B[39;49m\u001B[43m)\u001B[49m\n\u001B[1;32m 218\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28minput\u001B[39m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1511\u001B[0m, in \u001B[0;36mModule._wrapped_call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1510\u001B[0m \u001B[38;5;28;01melse\u001B[39;00m:\n\u001B[0;32m-> 1511\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_call_impl\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/module.py:1520\u001B[0m, in \u001B[0;36mModule._call_impl\u001B[0;34m(self, *args, **kwargs)\u001B[0m\n\u001B[1;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[1;32m 1516\u001B[0m \u001B[38;5;66;03m# this function, and just call forward.\u001B[39;00m\n\u001B[1;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[1;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[1;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[0;32m-> 1520\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mforward_call\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43margs\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[38;5;241;43m*\u001B[39;49m\u001B[43mkwargs\u001B[49m\u001B[43m)\u001B[49m\n\u001B[1;32m 1522\u001B[0m \u001B[38;5;28;01mtry\u001B[39;00m:\n\u001B[1;32m 1523\u001B[0m result \u001B[38;5;241m=\u001B[39m \u001B[38;5;28;01mNone\u001B[39;00m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/linear.py:116\u001B[0m, in \u001B[0;36mLinear.forward\u001B[0;34m(self, input)\u001B[0m\n\u001B[1;32m 115\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mforward\u001B[39m(\u001B[38;5;28mself\u001B[39m, \u001B[38;5;28minput\u001B[39m: Tensor) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Tensor:\n\u001B[0;32m--> 116\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mF\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mlinear\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43minput\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mweight\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbias\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[0;31mTypeError\u001B[0m: linear(): argument 'input' (position 1) must be Tensor, not tuple"
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/conv.py:460\u001B[0m, in \u001B[0;36mConv2d.forward\u001B[0;34m(self, input)\u001B[0m\n\u001B[1;32m 459\u001B[0m \u001B[38;5;28;01mdef\u001B[39;00m \u001B[38;5;21mforward\u001B[39m(\u001B[38;5;28mself\u001B[39m, \u001B[38;5;28minput\u001B[39m: Tensor) \u001B[38;5;241m-\u001B[39m\u001B[38;5;241m>\u001B[39m Tensor:\n\u001B[0;32m--> 460\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43m_conv_forward\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43minput\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mweight\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mbias\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"File \u001B[0;32m/nix/store/4mv9lb8b1vjx88y2i7px1r2s8p3xlr7d-python3-3.11.9-env/lib/python3.11/site-packages/torch/nn/modules/conv.py:456\u001B[0m, in \u001B[0;36mConv2d._conv_forward\u001B[0;34m(self, input, weight, bias)\u001B[0m\n\u001B[1;32m 452\u001B[0m \u001B[38;5;28;01mif\u001B[39;00m \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mpadding_mode \u001B[38;5;241m!=\u001B[39m \u001B[38;5;124m'\u001B[39m\u001B[38;5;124mzeros\u001B[39m\u001B[38;5;124m'\u001B[39m:\n\u001B[1;32m 453\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m F\u001B[38;5;241m.\u001B[39mconv2d(F\u001B[38;5;241m.\u001B[39mpad(\u001B[38;5;28minput\u001B[39m, \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39m_reversed_padding_repeated_twice, mode\u001B[38;5;241m=\u001B[39m\u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mpadding_mode),\n\u001B[1;32m 454\u001B[0m weight, bias, \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mstride,\n\u001B[1;32m 455\u001B[0m _pair(\u001B[38;5;241m0\u001B[39m), \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mdilation, \u001B[38;5;28mself\u001B[39m\u001B[38;5;241m.\u001B[39mgroups)\n\u001B[0;32m--> 456\u001B[0m \u001B[38;5;28;01mreturn\u001B[39;00m \u001B[43mF\u001B[49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mconv2d\u001B[49m\u001B[43m(\u001B[49m\u001B[38;5;28;43minput\u001B[39;49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mweight\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[43mbias\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mstride\u001B[49m\u001B[43m,\u001B[49m\n\u001B[1;32m 457\u001B[0m \u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mpadding\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mdilation\u001B[49m\u001B[43m,\u001B[49m\u001B[43m \u001B[49m\u001B[38;5;28;43mself\u001B[39;49m\u001B[38;5;241;43m.\u001B[39;49m\u001B[43mgroups\u001B[49m\u001B[43m)\u001B[49m\n",
|
||||
"\u001B[0;31mRuntimeError\u001B[0m: Given groups=1, weight of size [32, 1, 3, 3], expected input[32, 6, 16, 16] to have 1 channels, but got 6 channels instead"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"# Split train and test\n",
|
||||
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=2)\n",
|
||||
"X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1)\n",
|
||||
"\n",
|
||||
"# Filter test data that contains no labels\n",
|
||||
"# In Coursemology, the test data is guaranteed to have labels\n",
|
||||
@@ -502,14 +577,12 @@
|
||||
"\n",
|
||||
"# Train and predict\n",
|
||||
"model = Model()\n",
|
||||
"# model.fit(X_train, y_train)\n",
|
||||
"model.fit(X_train, y_train)\n",
|
||||
"y_pred = model.predict(X_test)\n",
|
||||
"print(y_pred[0])\n",
|
||||
"print(y[0])\n",
|
||||
"\n",
|
||||
"# Evaluate model predition\n",
|
||||
"# Learn more: https://scikit-learn.org/stable/modules/classes.html#module-sklearn.metrics\n",
|
||||
"# print(\"F1 Score (macro): {0:.2f}\".format(f1_score(y_test, y_pred, average='macro'))) # You may encounter errors, you are expected to figure out what's the issue."
|
||||
"print(\"F1 Score (macro): {0:.2f}\".format(f1_score(y_test, y_pred, average='macro'))) # You may encounter errors, you are expected to figure out what's the issue."
|
||||
]
|
||||
},
|
||||
{
|
||||
|
||||
Reference in New Issue
Block a user