Upload train-big.ipynb
Browse files- train-big.ipynb +1 -0
train-big.ipynb
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.14","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":3004,"databundleVersionId":861823,"sourceType":"competition"}],"dockerImageVersionId":30776,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"import torch\nimport torchvision\nimport torch.nn as nn\nimport torch.optim as optim\nimport torchvision.transforms as transforms\nfrom torchvision.models import resnet50, ResNet50_Weights\nimport torchvision.datasets as datasets\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\n# Load CIFAR-10 dataset\ntransform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))])\ntrain_dataset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)\ntest_dataset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)\ntrain_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=64, shuffle=True)\ntest_loader = torch.utils.data.DataLoader(dataset=test_dataset, batch_size=64, shuffle=False)\n\n# Define the teacher model\nbig = resnet50(weights=ResNet50_Weights.DEFAULT)\nbig.fc = nn.Linear(2048, 10) # CIFAR-10 has 10 classes\nbig = big.to(device)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:04:38.131610Z","iopub.execute_input":"2024-10-03T16:04:38.131979Z","iopub.status.idle":"2024-10-03T16:04:51.265885Z","shell.execute_reply.started":"2024-10-03T16:04:38.131941Z","shell.execute_reply":"2024-10-03T16:04:51.264789Z"},"trusted":true},"execution_count":1,"outputs":[{"name":"stdout","text":"Downloading https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz to ./data/cifar-10-python.tar.gz\n","output_type":"stream"},{"name":"stderr","text":"100%|██████████| 170498071/170498071 [00:02<00:00, 58728394.37it/s]\n","output_type":"stream"},{"name":"stdout","text":"Extracting ./data/cifar-10-python.tar.gz to ./data\nFiles already downloaded and verified\n","output_type":"stream"},{"name":"stderr","text":"Downloading: \"https://download.pytorch.org/models/resnet50-11ad3fa6.pth\" to /root/.cache/torch/hub/checkpoints/resnet50-11ad3fa6.pth\n100%|██████████| 97.8M/97.8M [00:00<00:00, 175MB/s] \n","output_type":"stream"}]},{"cell_type":"code","source":"# Using pytorch train/test function\ndef train(model, train_loader, epochs, learning_rate, device):\n criterion = nn.CrossEntropyLoss()\n optimizer = optim.Adam(model.parameters(), lr=learning_rate)\n\n model.train()\n\n for epoch in range(epochs):\n running_loss = 0.0\n for inputs, labels in train_loader:\n # inputs: A collection of batch_size images\n # labels: A vector of dimensionality batch_size with integers denoting class of each image\n inputs, labels = inputs.to(device), labels.to(device)\n\n optimizer.zero_grad()\n outputs = model(inputs)\n\n # outputs: Output of the network for the collection of images. A tensor of dimensionality batch_size x num_classes\n # labels: The actual labels of the images. Vector of dimensionality batch_size\n loss = criterion(outputs, labels)\n loss.backward()\n optimizer.step()\n\n running_loss += loss.item()\n\n print(f\"Epoch {epoch+1}/{epochs}, Loss: {running_loss / len(train_loader)}\")\n\ndef test(model, test_loader, device):\n model.to(device)\n model.eval()\n\n correct = 0\n total = 0\n\n with torch.no_grad():\n for inputs, labels in test_loader:\n inputs, labels = inputs.to(device), labels.to(device)\n\n outputs = model(inputs)\n _, predicted = torch.max(outputs.data, 1)\n\n total += labels.size(0)\n correct += (predicted == labels).sum().item()\n\n accuracy = 100 * correct / total\n print(f\"Test Accuracy: {accuracy:.2f}%\")\n return accuracy","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:04:51.267687Z","iopub.execute_input":"2024-10-03T16:04:51.268276Z","iopub.status.idle":"2024-10-03T16:04:51.279990Z","shell.execute_reply.started":"2024-10-03T16:04:51.268219Z","shell.execute_reply":"2024-10-03T16:04:51.279030Z"},"trusted":true},"execution_count":2,"outputs":[]},{"cell_type":"code","source":"torch.manual_seed(1337)\ntrain(big, train_loader, epochs=25, learning_rate=0.001, device=device)\n","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:04:51.281474Z","iopub.execute_input":"2024-10-03T16:04:51.281886Z","iopub.status.idle":"2024-10-03T16:25:44.301583Z","shell.execute_reply.started":"2024-10-03T16:04:51.281835Z","shell.execute_reply":"2024-10-03T16:25:44.299569Z"},"trusted":true},"execution_count":3,"outputs":[{"name":"stdout","text":"Epoch 1/100, Loss: 0.8542284834034303\nEpoch 2/100, Loss: 0.524260084571131\nEpoch 3/100, Loss: 0.40751915211644013\nEpoch 4/100, Loss: 0.33506347104678375\nEpoch 5/100, Loss: 0.2807430756537963\nEpoch 6/100, Loss: 0.23935459727597663\nEpoch 7/100, Loss: 0.1934807303282992\nEpoch 8/100, Loss: 0.17597612570685423\nEpoch 9/100, Loss: 0.1497522130908678\nEpoch 10/100, Loss: 0.13958692814216322\nEpoch 11/100, Loss: 0.12187561963963539\nEpoch 12/100, Loss: 0.10904402541213423\nEpoch 13/100, Loss: 0.09520113381528583\nEpoch 14/100, Loss: 0.08913293076426629\nEpoch 15/100, Loss: 0.08231373289314187\nEpoch 16/100, Loss: 0.0905858146585286\nEpoch 17/100, Loss: 0.075422206604758\nEpoch 18/100, Loss: 0.06664178025988562\nEpoch 19/100, Loss: 0.06412103258551496\nEpoch 20/100, Loss: 0.07453807451374606\nEpoch 21/100, Loss: 0.26053578569494246\nEpoch 22/100, Loss: 0.16313986415106\nEpoch 23/100, Loss: 0.10419799192407218\nEpoch 24/100, Loss: 0.07561451376384824\nEpoch 25/100, Loss: 0.05469732786003408\n","output_type":"stream"},{"traceback":["\u001b[0;31m---------------------------------------------------------------------------\u001b[0m","\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)","Cell \u001b[0;32mIn[3], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m torch\u001b[38;5;241m.\u001b[39mmanual_seed(\u001b[38;5;241m1337\u001b[39m)\n\u001b[0;32m----> 2\u001b[0m \u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbig\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtrain_loader\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m100\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlearning_rate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m0.001\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdevice\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 3\u001b[0m test_accuracy_deep \u001b[38;5;241m=\u001b[39m test(nn_deep, test_loader, device)\n","Cell \u001b[0;32mIn[2], line 24\u001b[0m, in \u001b[0;36mtrain\u001b[0;34m(model, train_loader, epochs, learning_rate, device)\u001b[0m\n\u001b[1;32m 21\u001b[0m loss\u001b[38;5;241m.\u001b[39mbackward()\n\u001b[1;32m 22\u001b[0m optimizer\u001b[38;5;241m.\u001b[39mstep()\n\u001b[0;32m---> 24\u001b[0m running_loss \u001b[38;5;241m+\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[43mloss\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mitem\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mEpoch \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mepoch\u001b[38;5;241m+\u001b[39m\u001b[38;5;241m1\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mepochs\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m, Loss: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrunning_loss\u001b[38;5;250m \u001b[39m\u001b[38;5;241m/\u001b[39m\u001b[38;5;250m \u001b[39m\u001b[38;5;28mlen\u001b[39m(train_loader)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n","\u001b[0;31mKeyboardInterrupt\u001b[0m: "],"ename":"KeyboardInterrupt","evalue":"","output_type":"error"}]},{"cell_type":"code","source":"test_accuracy_deep = test(big, test_loader, device)","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:26:02.421205Z","iopub.execute_input":"2024-10-03T16:26:02.421605Z","iopub.status.idle":"2024-10-03T16:26:07.067362Z","shell.execute_reply.started":"2024-10-03T16:26:02.421567Z","shell.execute_reply":"2024-10-03T16:26:07.066237Z"},"trusted":true},"execution_count":5,"outputs":[{"name":"stdout","text":"Test Accuracy: 85.11%\n","output_type":"stream"}]},{"cell_type":"code","source":"torch.save(big.state_dict(), \"./model\")","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:27:59.893904Z","iopub.execute_input":"2024-10-03T16:27:59.894735Z","iopub.status.idle":"2024-10-03T16:28:00.095601Z","shell.execute_reply.started":"2024-10-03T16:27:59.894687Z","shell.execute_reply":"2024-10-03T16:28:00.094690Z"},"trusted":true},"execution_count":6,"outputs":[]},{"cell_type":"code","source":"big.eval()","metadata":{"execution":{"iopub.status.busy":"2024-10-03T16:35:42.948737Z","iopub.execute_input":"2024-10-03T16:35:42.949143Z","iopub.status.idle":"2024-10-03T16:35:42.961205Z","shell.execute_reply.started":"2024-10-03T16:35:42.949105Z","shell.execute_reply":"2024-10-03T16:35:42.960226Z"},"trusted":true},"execution_count":7,"outputs":[{"execution_count":7,"output_type":"execute_result","data":{"text/plain":"ResNet(\n (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n (layer1): Sequential(\n (0): Bottleneck(\n (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n (downsample): Sequential(\n (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n )\n )\n (1): Bottleneck(\n (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (2): Bottleneck(\n (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n )\n (layer2): Sequential(\n (0): Bottleneck(\n (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n (downsample): Sequential(\n (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)\n (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n )\n )\n (1): Bottleneck(\n (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (2): Bottleneck(\n (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (3): Bottleneck(\n (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n )\n (layer3): Sequential(\n (0): Bottleneck(\n (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n (downsample): Sequential(\n (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)\n (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n )\n )\n (1): Bottleneck(\n (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (2): Bottleneck(\n (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (3): Bottleneck(\n (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (4): Bottleneck(\n (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (5): Bottleneck(\n (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n )\n (layer4): Sequential(\n (0): Bottleneck(\n (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n (downsample): Sequential(\n (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)\n (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n )\n )\n (1): Bottleneck(\n (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n (2): Bottleneck(\n (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)\n (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n (relu): ReLU(inplace=True)\n )\n )\n (avgpool): AdaptiveAvgPool2d(output_size=(1, 1))\n (fc): Linear(in_features=2048, out_features=10, bias=True)\n)"},"metadata":{}}]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}
|