diff --git a/python/Deep Learning/Deep Learning with PyTorch/Part 8 - Transfer Learning (Exercises).ipynb b/python/Deep Learning/Deep Learning with PyTorch/Part 8 - Transfer Learning (Exercises).ipynb index b385c7a..f2543c7 100644 --- a/python/Deep Learning/Deep Learning with PyTorch/Part 8 - Transfer Learning (Exercises).ipynb +++ b/python/Deep Learning/Deep Learning with PyTorch/Part 8 - Transfer Learning (Exercises).ipynb @@ -658,16 +658,16 @@ }, { "cell_type": "code", - "execution_count": 11, + "execution_count": 6, "metadata": {}, "outputs": [ { "data": { "text/plain": [ - "False" + "True" ] }, - "execution_count": 11, + "execution_count": 6, "metadata": {}, "output_type": "execute_result" } @@ -678,7 +678,7 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "metadata": {}, "outputs": [ { @@ -687,7 +687,7 @@ "True" ] }, - "execution_count": 10, + "execution_count": 7, "metadata": {}, "output_type": "execute_result" } @@ -698,32 +698,15 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "Device = cpu; Time per batch: 2.646 seconds\n" - ] - }, - { - "ename": "AssertionError", - "evalue": "Torch not compiled with CUDA enabled", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mAssertionError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0moptimizer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0moptim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mAdam\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclassifier\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mparameters\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlr\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.001\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 6\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 7\u001b[1;33m \u001b[0mmodel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 8\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 9\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mii\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtrainloader\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36mto\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m 379\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_floating_point\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32melse\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_blocking\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 380\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 381\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mconvert\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 382\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 383\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mregister_backward_hook\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhook\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_apply\u001b[1;34m(self, fn)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mmodule\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mchildren\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mmodule\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_parameters\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_apply\u001b[1;34m(self, fn)\u001b[0m\n\u001b[0;32m 185\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 186\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mmodule\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mchildren\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 187\u001b[1;33m \u001b[0mmodule\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 188\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mparam\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_parameters\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36m_apply\u001b[1;34m(self, fn)\u001b[0m\n\u001b[0;32m 191\u001b[0m \u001b[1;31m# Tensors stored in modules are graph leaves, and we don't\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 192\u001b[0m \u001b[1;31m# want to create copy nodes, so we have to unpack the data.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 193\u001b[1;33m \u001b[0mparam\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 194\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mparam\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_grad\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 195\u001b[0m \u001b[0mparam\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_grad\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mfn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mparam\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_grad\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\nn\\modules\\module.py\u001b[0m in \u001b[0;36mconvert\u001b[1;34m(t)\u001b[0m\n\u001b[0;32m 377\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 378\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mconvert\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mt\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 379\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mis_floating_point\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32melse\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnon_blocking\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 380\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 381\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_apply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mconvert\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\cuda\\__init__.py\u001b[0m in \u001b[0;36m_lazy_init\u001b[1;34m()\u001b[0m\n\u001b[0;32m 159\u001b[0m raise RuntimeError(\n\u001b[0;32m 160\u001b[0m \"Cannot re-initialize CUDA in forked subprocess. \" + msg)\n\u001b[1;32m--> 161\u001b[1;33m \u001b[0m_check_driver\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 162\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_cuda_init\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 163\u001b[0m \u001b[0m_cudart\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_load_cudart\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\cuda\\__init__.py\u001b[0m in \u001b[0;36m_check_driver\u001b[1;34m()\u001b[0m\n\u001b[0;32m 73\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0m_check_driver\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 74\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'_cuda_isDriverSufficient'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 75\u001b[1;33m \u001b[1;32mraise\u001b[0m \u001b[0mAssertionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Torch not compiled with CUDA enabled\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 76\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_cuda_isDriverSufficient\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 77\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_C\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_cuda_getDriverVersion\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mAssertionError\u001b[0m: Torch not compiled with CUDA enabled" + "Device = cpu; Time per batch: 2.370 seconds\n", + "Device = cuda; Time per batch: 0.019 seconds\n" ] } ], @@ -778,23 +761,521 @@ }, { "cell_type": "code", - "execution_count": 5, + "execution_count": 9, "metadata": {}, "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/opt/conda/lib/python3.6/site-packages/torchvision-0.2.1-py3.6.egg/torchvision/models/densenet.py:212: UserWarning: nn.init.kaiming_normal is now deprecated in favor of nn.init.kaiming_normal_.\n" - ] - }, { "data": { "text/plain": [ - "device(type='cuda')" + "DenseNet(\n", + " (features): Sequential(\n", + " (conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)\n", + " (norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu0): ReLU(inplace)\n", + " (pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)\n", + " (denseblock1): _DenseBlock(\n", + " (denselayer1): _DenseLayer(\n", + " (norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer2): _DenseLayer(\n", + " (norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer3): _DenseLayer(\n", + " (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer4): _DenseLayer(\n", + " (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer5): _DenseLayer(\n", + " (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer6): _DenseLayer(\n", + " (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " )\n", + " (transition1): _Transition(\n", + " (norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu): ReLU(inplace)\n", + " (conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n", + " )\n", + " (denseblock2): _DenseBlock(\n", + " (denselayer1): _DenseLayer(\n", + " (norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer2): _DenseLayer(\n", + " (norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer3): _DenseLayer(\n", + " (norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer4): _DenseLayer(\n", + " (norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer5): _DenseLayer(\n", + " (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer6): _DenseLayer(\n", + " (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer7): _DenseLayer(\n", + " (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer8): _DenseLayer(\n", + " (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer9): _DenseLayer(\n", + " (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer10): _DenseLayer(\n", + " (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer11): _DenseLayer(\n", + " (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer12): _DenseLayer(\n", + " (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " )\n", + " (transition2): _Transition(\n", + " (norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu): ReLU(inplace)\n", + " (conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n", + " )\n", + " (denseblock3): _DenseBlock(\n", + " (denselayer1): _DenseLayer(\n", + " (norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer2): _DenseLayer(\n", + " (norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer3): _DenseLayer(\n", + " (norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer4): _DenseLayer(\n", + " (norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer5): _DenseLayer(\n", + " (norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer6): _DenseLayer(\n", + " (norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer7): _DenseLayer(\n", + " (norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer8): _DenseLayer(\n", + " (norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer9): _DenseLayer(\n", + " (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer10): _DenseLayer(\n", + " (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer11): _DenseLayer(\n", + " (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer12): _DenseLayer(\n", + " (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer13): _DenseLayer(\n", + " (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer14): _DenseLayer(\n", + " (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer15): _DenseLayer(\n", + " (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer16): _DenseLayer(\n", + " (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer17): _DenseLayer(\n", + " (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer18): _DenseLayer(\n", + " (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer19): _DenseLayer(\n", + " (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer20): _DenseLayer(\n", + " (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer21): _DenseLayer(\n", + " (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer22): _DenseLayer(\n", + " (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer23): _DenseLayer(\n", + " (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer24): _DenseLayer(\n", + " (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " )\n", + " (transition3): _Transition(\n", + " (norm): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu): ReLU(inplace)\n", + " (conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (pool): AvgPool2d(kernel_size=2, stride=2, padding=0)\n", + " )\n", + " (denseblock4): _DenseBlock(\n", + " (denselayer1): _DenseLayer(\n", + " (norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer2): _DenseLayer(\n", + " (norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer3): _DenseLayer(\n", + " (norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer4): _DenseLayer(\n", + " (norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer5): _DenseLayer(\n", + " (norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer6): _DenseLayer(\n", + " (norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer7): _DenseLayer(\n", + " (norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer8): _DenseLayer(\n", + " (norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer9): _DenseLayer(\n", + " (norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer10): _DenseLayer(\n", + " (norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer11): _DenseLayer(\n", + " (norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer12): _DenseLayer(\n", + " (norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer13): _DenseLayer(\n", + " (norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer14): _DenseLayer(\n", + " (norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer15): _DenseLayer(\n", + " (norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " (denselayer16): _DenseLayer(\n", + " (norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu1): ReLU(inplace)\n", + " (conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)\n", + " (norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " (relu2): ReLU(inplace)\n", + " (conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)\n", + " )\n", + " )\n", + " (norm5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n", + " )\n", + " (classifier): Sequential(\n", + " (0): Linear(in_features=1024, out_features=256, bias=True)\n", + " (1): ReLU()\n", + " (2): Dropout(p=0.2)\n", + " (3): Linear(in_features=256, out_features=2, bias=True)\n", + " (4): LogSoftmax()\n", + " )\n", + ")" ] }, - "execution_count": 5, + "execution_count": 9, "metadata": {}, "output_type": "execute_result" } @@ -822,13 +1303,12 @@ "# Only train the classifier parameters, feature parameters are frozen\n", "optimizer = optim.Adam(model.classifier.parameters(), lr=0.003)\n", "\n", - "model.to(device)\n", - "device" + "model.to(device)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "metadata": {}, "outputs": [ { @@ -836,21 +1316,109 @@ "output_type": "stream", "text": [ "Epoch: 1 out of 1\n", - "Training Loss: 0.208\n", - "Test Loss: 0.076\n", - "Test Accuracy: 0.971\n", + "Training Loss: 0.745\n", + "Test Loss: 0.237\n", + "Test Accuracy: 0.968\n", "\n", "Epoch: 1 out of 1\n", - "Training Loss: 0.214\n", - "Test Loss: 0.068\n", + "Training Loss: 0.335\n", + "Test Loss: 0.124\n", + "Test Accuracy: 0.969\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.197\n", + "Test Loss: 0.073\n", "Test Accuracy: 0.978\n", "\n", "Epoch: 1 out of 1\n", - "Training Loss: 0.216\n", - "Test Loss: 0.075\n", - "Test Accuracy: 0.971\n", + "Training Loss: 0.248\n", + "Test Loss: 0.066\n", + "Test Accuracy: 0.978\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.203\n", + "Test Loss: 0.067\n", + "Test Accuracy: 0.976\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.223\n", + "Test Loss: 0.053\n", + "Test Accuracy: 0.980\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.174\n", + "Test Loss: 0.051\n", + "Test Accuracy: 0.982\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.111\n", + "Test Loss: 0.051\n", + "Test Accuracy: 0.980\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.158\n", + "Test Loss: 0.046\n", + "Test Accuracy: 0.982\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.136\n", + "Test Loss: 0.046\n", + "Test Accuracy: 0.985\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.174\n", + "Test Loss: 0.057\n", + "Test Accuracy: 0.977\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.170\n", + "Test Loss: 0.050\n", + "Test Accuracy: 0.984\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.179\n", + "Test Loss: 0.046\n", + "Test Accuracy: 0.984\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.207\n", + "Test Loss: 0.051\n", + "Test Accuracy: 0.982\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.204\n", + "Test Loss: 0.111\n", + "Test Accuracy: 0.961\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.233\n", + "Test Loss: 0.164\n", + "Test Accuracy: 0.935\n", + "\n", + "Epoch: 1 out of 1\n", + "Training Loss: 0.367\n", + "Test Loss: 0.191\n", + "Test Accuracy: 0.919\n", "\n" ] + }, + { + "ename": "KeyboardInterrupt", + "evalue": "", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", + "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 35\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 36\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0mtorch\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mno_grad\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 37\u001b[1;33m \u001b[1;32mfor\u001b[0m \u001b[0minputs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mtestloader\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 38\u001b[0m \u001b[1;31m# Move input and label tensors to the device\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 39\u001b[0m \u001b[0minputs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minputs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlabels\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mto\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdevice\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\utils\\data\\dataloader.py\u001b[0m in \u001b[0;36m__next__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 558\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnum_workers\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;31m# same-process loading\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 559\u001b[0m \u001b[0mindices\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msample_iter\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# may raise StopIteration\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 560\u001b[1;33m \u001b[0mbatch\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcollate_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mindices\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 561\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 562\u001b[0m \u001b[0mbatch\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_utils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory_batch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torch\\utils\\data\\dataloader.py\u001b[0m in \u001b[0;36m\u001b[1;34m(.0)\u001b[0m\n\u001b[0;32m 558\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnum_workers\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;31m# same-process loading\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 559\u001b[0m \u001b[0mindices\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msample_iter\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;31m# may raise StopIteration\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 560\u001b[1;33m \u001b[0mbatch\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcollate_fn\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mindices\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 561\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 562\u001b[0m \u001b[0mbatch\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_utils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpin_memory_batch\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torchvision\\datasets\\folder.py\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, index)\u001b[0m\n\u001b[0;32m 136\u001b[0m \"\"\"\n\u001b[0;32m 137\u001b[0m \u001b[0mpath\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtarget\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msamples\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 138\u001b[1;33m \u001b[0msample\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloader\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 139\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtransform\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 140\u001b[0m \u001b[0msample\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msample\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torchvision\\datasets\\folder.py\u001b[0m in \u001b[0;36mdefault_loader\u001b[1;34m(path)\u001b[0m\n\u001b[0;32m 172\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0maccimage_loader\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 173\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 174\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mpil_loader\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 175\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 176\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\torchvision\\datasets\\folder.py\u001b[0m in \u001b[0;36mpil_loader\u001b[1;34m(path)\u001b[0m\n\u001b[0;32m 155\u001b[0m \u001b[1;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'rb'\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 156\u001b[0m \u001b[0mimg\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mImage\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mopen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 157\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mimg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconvert\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'RGB'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 158\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 159\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\PIL\\Image.py\u001b[0m in \u001b[0;36mconvert\u001b[1;34m(self, mode, matrix, dither, palette, colors)\u001b[0m\n\u001b[0;32m 913\u001b[0m \"\"\"\n\u001b[0;32m 914\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 915\u001b[1;33m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 916\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 917\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mmode\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmode\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m\"P\"\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;32m~\\Anaconda3\\lib\\site-packages\\PIL\\ImageFile.py\u001b[0m in \u001b[0;36mload\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 239\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 240\u001b[0m \u001b[0mb\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mb\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0ms\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 241\u001b[1;33m \u001b[0mn\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0merr_code\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdecoder\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdecode\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 242\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mn\u001b[0m \u001b[1;33m<\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 243\u001b[0m \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", + "\u001b[1;31mKeyboardInterrupt\u001b[0m: " + ] } ], "source": [ @@ -925,6 +1493,15 @@ " model.train()" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "device" + ] + }, { "cell_type": "code", "execution_count": null, diff --git a/python/Deep Learning/Deep Learning with PyTorch/Untitled.ipynb b/python/Deep Learning/Deep Learning with PyTorch/Untitled.ipynb deleted file mode 100644 index 08ec6ba..0000000 --- a/python/Deep Learning/Deep Learning with PyTorch/Untitled.ipynb +++ /dev/null @@ -1,332 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "torch.Size([64, 10])\n", - "tensor([[9],\n", - " [9],\n", - " [9],\n", - " [9],\n", - " [9],\n", - " [5],\n", - " [9],\n", - " [5],\n", - " [2],\n", - " [9]])\n", - "Accuracy: 1.5625%\n", - "Epoch: 1 out of 30\n", - "Training Loss: 0.510\n", - "Test Loss: 0.454\n", - "Test Accuracy: 0.836\n", - "\n", - "Epoch: 2 out of 30\n", - "Training Loss: 0.389\n", - "Test Loss: 0.412\n", - "Test Accuracy: 0.852\n", - "\n", - "Epoch: 3 out of 30\n", - "Training Loss: 0.353\n", - "Test Loss: 0.388\n", - "Test Accuracy: 0.861\n", - "\n", - "Epoch: 4 out of 30\n", - "Training Loss: 0.330\n", - "Test Loss: 0.428\n", - "Test Accuracy: 0.847\n", - "\n", - "Epoch: 5 out of 30\n", - "Training Loss: 0.315\n", - "Test Loss: 0.381\n", - "Test Accuracy: 0.865\n", - "\n", - "Epoch: 6 out of 30\n", - "Training Loss: 0.303\n", - "Test Loss: 0.388\n", - "Test Accuracy: 0.864\n", - "\n", - "Epoch: 7 out of 30\n", - "Training Loss: 0.292\n", - "Test Loss: 0.364\n", - "Test Accuracy: 0.872\n", - "\n", - "Epoch: 8 out of 30\n", - "Training Loss: 0.281\n", - "Test Loss: 0.370\n", - "Test Accuracy: 0.869\n", - "\n", - "Epoch: 9 out of 30\n", - "Training Loss: 0.270\n", - "Test Loss: 0.365\n", - "Test Accuracy: 0.877\n", - "\n", - "Epoch: 10 out of 30\n", - "Training Loss: 0.267\n", - "Test Loss: 0.366\n", - "Test Accuracy: 0.877\n", - "\n", - "Epoch: 11 out of 30\n", - "Training Loss: 0.260\n", - "Test Loss: 0.369\n", - "Test Accuracy: 0.873\n", - "\n", - "Epoch: 12 out of 30\n", - "Training Loss: 0.254\n", - "Test Loss: 0.377\n", - "Test Accuracy: 0.876\n", - "\n", - "Epoch: 13 out of 30\n", - "Training Loss: 0.244\n", - "Test Loss: 0.369\n", - "Test Accuracy: 0.879\n", - "\n", - "Epoch: 14 out of 30\n", - "Training Loss: 0.243\n", - "Test Loss: 0.371\n", - "Test Accuracy: 0.879\n", - "\n", - "Epoch: 15 out of 30\n", - "Training Loss: 0.237\n", - "Test Loss: 0.377\n", - "Test Accuracy: 0.883\n", - "\n", - "Epoch: 16 out of 30\n", - "Training Loss: 0.230\n", - "Test Loss: 0.407\n", - "Test Accuracy: 0.874\n", - "\n", - "Epoch: 17 out of 30\n", - "Training Loss: 0.228\n", - "Test Loss: 0.370\n", - "Test Accuracy: 0.879\n", - "\n", - "Epoch: 18 out of 30\n", - "Training Loss: 0.221\n", - "Test Loss: 0.376\n", - "Test Accuracy: 0.878\n", - "\n", - "Epoch: 19 out of 30\n", - "Training Loss: 0.222\n", - "Test Loss: 0.376\n", - "Test Accuracy: 0.881\n", - "\n", - "Epoch: 20 out of 30\n", - "Training Loss: 0.217\n", - "Test Loss: 0.387\n", - "Test Accuracy: 0.880\n", - "\n", - "Epoch: 21 out of 30\n", - "Training Loss: 0.209\n", - "Test Loss: 0.401\n", - "Test Accuracy: 0.877\n", - "\n", - "Epoch: 22 out of 30\n", - "Training Loss: 0.210\n", - "Test Loss: 0.392\n", - "Test Accuracy: 0.883\n", - "\n", - "Epoch: 23 out of 30\n", - "Training Loss: 0.204\n", - "Test Loss: 0.411\n", - "Test Accuracy: 0.878\n", - "\n", - "Epoch: 24 out of 30\n", - "Training Loss: 0.202\n", - "Test Loss: 0.391\n", - "Test Accuracy: 0.882\n", - "\n", - "Epoch: 25 out of 30\n", - "Training Loss: 0.195\n", - "Test Loss: 0.392\n", - "Test Accuracy: 0.883\n", - "\n", - "Epoch: 26 out of 30\n", - "Training Loss: 0.195\n", - "Test Loss: 0.471\n", - "Test Accuracy: 0.878\n", - "\n", - "Epoch: 27 out of 30\n", - "Training Loss: 0.191\n", - "Test Loss: 0.431\n", - "Test Accuracy: 0.881\n", - "\n", - "Epoch: 28 out of 30\n", - "Training Loss: 0.195\n", - "Test Loss: 0.418\n", - "Test Accuracy: 0.882\n", - "\n", - "Epoch: 29 out of 30\n", - "Training Loss: 0.192\n", - "Test Loss: 0.390\n", - "Test Accuracy: 0.887\n", - "\n", - "Epoch: 30 out of 30\n", - "Training Loss: 0.185\n", - "Test Loss: 0.428\n", - "Test Accuracy: 0.875\n", - "\n" - ] - } - ], - "source": [ - "import torch\n", - "from torchvision import datasets, transforms\n", - "from torch import nn, optim\n", - "import torch.nn.functional as F\n", - "\n", - "# Define a transform to normalize the data\n", - "transform = transforms.Compose([transforms.ToTensor(),\n", - " transforms.Normalize((0.5, 0.5, 0.5),\n", - " (0.5, 0.5, 0.5))])\n", - "\n", - "# Download and load the training data\n", - "trainset = datasets.FashionMNIST(\n", - " '.pytorch/F_MNIST_data/', download=True, train=True, transform=transform)\n", - "\n", - "trainloader = torch.utils.data.DataLoader(\n", - " trainset, batch_size=64, shuffle=True)\n", - "\n", - "# Download and load the test data\n", - "testset = datasets.FashionMNIST(\n", - " '.pytorch/F_MNIST_data/', download=True, train=False,\n", - " transform=transform)\n", - "\n", - "testloader = torch.utils.data.DataLoader(testset, batch_size=64, shuffle=True)\n", - "\n", - "\n", - "class Classifier(nn.Module):\n", - " def __init__(self):\n", - " super().__init__()\n", - " self.fc1 = nn.Linear(784, 256)\n", - " self.fc2 = nn.Linear(256, 128)\n", - " self.fc3 = nn.Linear(128, 64)\n", - " self.fc4 = nn.Linear(64, 10)\n", - "\n", - " def forward(self, x):\n", - " # make sure input tensor is flattened\n", - " x = x.view(x.shape[0], -1)\n", - "\n", - " x = F.relu(self.fc1(x))\n", - " x = F.relu(self.fc2(x))\n", - " x = F.relu(self.fc3(x))\n", - " x = F.log_softmax(self.fc4(x), dim=1)\n", - "\n", - " return x\n", - "\n", - "\n", - "model = Classifier()\n", - "\n", - "images, labels = next(iter(testloader))\n", - "\n", - "# Get the class probabilities\n", - "ps = torch.exp(model(images))\n", - "\n", - "# Make sure the shape is appropriate, we should get 10 class probabilities for\n", - "# 64 examples\n", - "print(ps.shape)\n", - "\n", - "top_p, top_class = ps.topk(1, dim=1)\n", - "# Look at the most likely classes for the first 10 examples\n", - "print(top_class[:10, :])\n", - "\n", - "\n", - "equals = top_class == labels.view(*top_class.shape)\n", - "\n", - "\n", - "accuracy = torch.mean(equals.type(torch.FloatTensor))\n", - "print(f'Accuracy: {accuracy.item()*100}%')\n", - "\n", - "\n", - "# Model begins\n", - "\n", - "model = Classifier()\n", - "criterion = nn.NLLLoss()\n", - "optimizer = optim.Adam(model.parameters(), lr=0.003)\n", - "\n", - "epochs = 30\n", - "steps = 0\n", - "\n", - "trainLosses, testLosses = [], []\n", - "for e in range(epochs):\n", - " runningLoss = 0\n", - " for images, labels in trainloader:\n", - "\n", - " optimizer.zero_grad()\n", - "\n", - " log_ps = model(images)\n", - " loss = criterion(log_ps, labels)\n", - " loss.backward()\n", - " optimizer.step()\n", - "\n", - " runningLoss += loss.item()\n", - "\n", - " else:\n", - " testLoss = 0\n", - " accuracy = 0\n", - "\n", - " # Turn off gradients for validation step\n", - " with torch.no_grad():\n", - " for images, labels in testloader:\n", - " # Get the output\n", - " log_ps = model(images)\n", - " # Get the loss\n", - " testLoss += criterion(log_ps, labels)\n", - "\n", - " # Get the probabilities\n", - " ps = torch.exp(log_ps)\n", - " # Get the most likely class for each prediction\n", - " top_p, top_class = ps.topk(1, dim=1)\n", - " # Check if the predictions match the actual label\n", - " equals = top_class == labels.view(*top_class.shape)\n", - " # Update accuracy\n", - " accuracy += torch.mean(equals.type(torch.FloatTensor))\n", - "\n", - " # Update train loss\n", - " trainLosses.append(runningLoss / len(trainloader))\n", - " # Update test loss\n", - " testLosses.append(testLoss / len(testloader))\n", - "\n", - " # Print output\n", - " print(f'Epoch: {e+1} out of {epochs}')\n", - " print(f'Training Loss: {runningLoss/len(trainloader):.3f}')\n", - " print(f'Test Loss: {testLoss/len(testloader):.3f}')\n", - " print(f'Test Accuracy: {accuracy/len(testloader):.3f}')\n", - " print()\n" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3", - "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": "3.7.3" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -}