{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# DL Project\n\n- Type: a competition-based project with a leader board (training datasets is released on lecture's kaggle competition page)\n\n- Objective: maximizing the test accuracy.\n\n- Period:\n - 11th Nov. to 9th Dec.\n\n- Evaluations: Final rank and presentations.\n\n- Additional points\n - (a) All participants are requested to present their methods and release the source codes.\n - (b) The final score should be reproducible by the shared codes.","metadata":{"id":"YfXDwvQT8yTQ"}},{"cell_type":"markdown","source":"## CAUTION\n\n- You can change **only** the **[Define Model](#scrollTo=9ViRr0JT84C7)**, **[Train Model](#scrollTo=NSFY5dyOm-qA)** and **[Hyperparameters](#scrollTo=Pv-hIWaJomEf)** sections.\n- You can use any kind of deep neural networks and apply any optimization techniques to improve the performance.","metadata":{"id":"3vNLbsjM9Ehu"}},{"cell_type":"markdown","source":"## Mount Google Drive and Download training&test datasets\n\nFirst, Download datasets from [this lecture's kaggle competition page](https://www.kaggle.com/c/ai700500-dl-project) and upload your Google Drive.\n\nThen, make a folder at the top of your Google Drive (`My Drive/AI700500_DL_Project/`).\n\n**You shuold upload dataset zip file to `My Drive/AI700500_DL_Project/`.**\n\nThen, mount your google drive on this session.","metadata":{"id":"1GvqrsV18zmq"}},{"cell_type":"code","source":"# check your GPU device\n!nvidia-smi","metadata":{"id":"ACB3M4zmPvQz","outputId":"3cf8ba82-5fdb-4bff-a603-c1af4702277f"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from google.colab import drive\n\n# Accessing My Google Drive\ndrive.mount('/content/drive')","metadata":{"id":"g0GlIuz18vuL","outputId":"4526b5fa-eb28-46b4-d3bd-91c75605219f"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### mount google drive example\n\n1. Execute the mount cell and click that https URL below picture \n![mount_4.png](data:image/png;base64,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)\n\n2. Click your account \n\n\n3. Click allow button \n\n\n4. Copy the authorization code \n\n\n\n5. Enter the authorization code \n![mount_4.png](data:image/png;base64,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)\n\n6. Done! \n![mount_5.png](data:image/png;base64,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)","metadata":{"id":"ftJ6Zg_JCxUo"}},{"cell_type":"markdown","source":"## Unzip dataset on runtime session","metadata":{"id":"ytAIwMpHDoFx"}},{"cell_type":"code","source":"!unzip '/content/drive/My Drive/AI700500_DL_Project/Stanford_40_Actions.zip'","metadata":{"id":"pGfZJQqFDuEF"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Define Model","metadata":{"id":"N1MCxs3h84lB"}},{"cell_type":"code","source":"### https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py\nimport torch\nimport torch.nn as nn\nfrom torchvision.models.utils import load_state_dict_from_url\n\n\ndef conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):\n \"\"\"3x3 convolution with padding\"\"\"\n return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,\n padding=dilation, groups=groups, bias=False, dilation=dilation)\n\ndef conv1x1(in_planes, out_planes, stride=1):\n \"\"\"1x1 convolution\"\"\"\n return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)\n\nclass BasicBlock(nn.Module):\n expansion = 1\n\n def __init__(self, inplanes, planes, stride=1, downsample=None, groups=1,\n base_width=64, dilation=1, norm_layer=None):\n super(BasicBlock, self).__init__()\n if norm_layer is None:\n norm_layer = nn.BatchNorm2d\n if groups != 1 or base_width != 64:\n raise ValueError('BasicBlock only supports groups=1 and base_width=64')\n if dilation > 1:\n raise NotImplementedError(\"Dilation > 1 not supported in BasicBlock\")\n # Both self.conv1 and self.downsample layers downsample the input when stride != 1\n self.conv1 = conv3x3(inplanes, planes, stride)\n self.bn1 = norm_layer(planes)\n self.relu = nn.ReLU(inplace=True)\n self.conv2 = conv3x3(planes, planes)\n self.bn2 = norm_layer(planes)\n self.downsample = downsample\n self.stride = stride\n\n def forward(self, x):\n identity = x\n\n out = self.conv1(x)\n out = self.bn1(out)\n out = self.relu(out)\n\n out = self.conv2(out)\n out = self.bn2(out)\n\n if self.downsample is not None:\n identity = self.downsample(x)\n\n out += identity\n out = self.relu(out)\n\n return out\n\n\nclass ResNet(nn.Module):\n def __init__(self, block, layers, num_classes=40, zero_init_residual=False,\n groups=1, width_per_group=64, replace_stride_with_dilation=None,\n norm_layer=None):\n super(ResNet, self).__init__()\n if norm_layer is None:\n norm_layer = nn.BatchNorm2d\n self._norm_layer = norm_layer\n\n self.inplanes = 64\n self.dilation = 1\n if replace_stride_with_dilation is None:\n # each element in the tuple indicates if we should replace\n # the 2x2 stride with a dilated convolution instead\n replace_stride_with_dilation = [False, False, False]\n if len(replace_stride_with_dilation) != 3:\n raise ValueError(\"replace_stride_with_dilation should be None \"\n \"or a 3-element tuple, got {}\".format(replace_stride_with_dilation))\n self.groups = groups\n self.base_width = width_per_group\n\n self.conv1 = nn.Conv2d(3, self.inplanes, kernel_size=7, stride=2, padding=3, # the first layer uses fp weights\n bias=False)\n self.bn1 = norm_layer(self.inplanes)\n self.relu = nn.ReLU(inplace=True)\n self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)\n self.layer1 = self._make_layer(block, 32, layers[0])\n self.layer2 = self._make_layer(block, 64, layers[1], stride=2,\n dilate=replace_stride_with_dilation[0])\n self.layer3 = self._make_layer(block, 128, layers[2], stride=2,\n dilate=replace_stride_with_dilation[1])\n self.layer4 = self._make_layer(block, 256, layers[3], stride=2,\n dilate=replace_stride_with_dilation[2])\n self.avgpool = nn.AdaptiveAvgPool2d((1, 1))\n self.fc = nn.Linear(256 * block.expansion, num_classes) # the last layer uses fp weights\n\n for m in self.modules():\n if isinstance(m, nn.Conv2d):\n nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')\n elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):\n nn.init.constant_(m.weight, 1)\n nn.init.constant_(m.bias, 0)\n\n # Zero-initialize the last BN in each residual branch,\n # so that the residual branch starts with zeros, and each residual block behaves like an identity.\n # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677\n if zero_init_residual:\n for m in self.modules():\n if isinstance(m, BasicBlock):\n nn.init.constant_(m.bn2.weight, 0)\n\n def _make_layer(self, block, planes, blocks, stride=1, dilate=False):\n norm_layer = self._norm_layer\n downsample = None\n previous_dilation = self.dilation\n if dilate:\n self.dilation *= stride\n stride = 1\n if stride != 1 or self.inplanes != planes * block.expansion:\n downsample = nn.Sequential(\n conv1x1(self.inplanes, planes * block.expansion, stride),\n norm_layer(planes * block.expansion),\n )\n\n layers = []\n layers.append(block(self.inplanes, planes, stride, downsample, self.groups,\n self.base_width, previous_dilation, norm_layer))\n self.inplanes = planes * block.expansion\n for _ in range(1, blocks):\n layers.append(block(self.inplanes, planes, groups=self.groups,\n base_width=self.base_width, dilation=self.dilation,\n norm_layer=norm_layer))\n\n return nn.Sequential(*layers)\n\n def _forward_impl(self, x):\n # See note [TorchScript super()]\n x = self.conv1(x)\n x = self.bn1(x)\n x = self.relu(x)\n x = self.maxpool(x)\n\n x = self.layer1(x)\n x = self.layer2(x)\n x = self.layer3(x)\n x = self.layer4(x)\n\n x = self.avgpool(x)\n x = torch.flatten(x, 1)\n x = self.fc(x)\n\n return x\n\n def forward(self, x):\n return self._forward_impl(x)\n\ndef resnet18():\n r\"\"\"ResNet-18 model from\n `\"Deep Residual Learning for Image Recognition\" `_\n \"\"\"\n model = ResNet(BasicBlock, [2, 2, 2, 2])\n return model\n","metadata":{"id":"nd4zFdb9M3Kw"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## utils","metadata":{"id":"1CDgUpDcmq6-"}},{"cell_type":"code","source":"class AverageMeter(object):\n r\"\"\"Computes and stores the average and current value\n \"\"\"\n def __init__(self, name, fmt=':f'):\n self.name = name\n self.fmt = fmt\n self.reset()\n\n def reset(self):\n self.val = 0\n self.avg = 0\n self.sum = 0\n self.count = 0\n\n def update(self, val, n=1):\n self.val = val\n self.sum += val * n\n self.count += n\n self.avg = self.sum / self.count\n\n def __str__(self):\n fmtstr = '{name} {val' + self.fmt + '} ({avg' + self.fmt + '})'\n return fmtstr.format(**self.__dict__)\n\n\nclass ProgressMeter(object):\n def __init__(self, num_batches, *meters, prefix=\"\"):\n self.batch_fmtstr = self._get_batch_fmtstr(num_batches)\n self.meters = meters\n self.prefix = prefix\n\n def print(self, batch):\n entries = [self.prefix + self.batch_fmtstr.format(batch)]\n entries += [str(meter) for meter in self.meters]\n print('\\t'.join(entries))\n\n def _get_batch_fmtstr(self, num_batches):\n num_digits = len(str(num_batches // 1))\n fmt = '{:' + str(num_digits) + 'd}'\n return '[' + fmt + '/' + fmt.format(num_batches) + ']'\n\n\ndef accuracy(output, target, topk=(1,)):\n r\"\"\"Computes the accuracy over the $k$ top predictions for the specified values of k\n \"\"\"\n with torch.no_grad():\n maxk = max(topk)\n batch_size = target.size(0)\n\n # _, pred = output.topk(maxk, 1, True, True)\n # pred = pred.t()\n # correct = pred.eq(target.view(1, -1).expand_as(pred))\n\n # faster topk (ref: https://github.com/pytorch/pytorch/issues/22812)\n _, idx = output.sort(descending=True)\n pred = idx[:,:maxk]\n pred = pred.t()\n correct = pred.eq(target.view(1, -1).expand_as(pred))\n\n res = []\n for k in topk:\n correct_k = correct[:k].reshape(-1).float().sum(0, keepdim=True)\n res.append(correct_k.mul_(100.0 / batch_size))\n return res","metadata":{"id":"aw4uo1CL9M7j"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Hyperparameters","metadata":{"id":"_SxkjBIxolsm"}},{"cell_type":"code","source":"SAVEPATH = '/content/drive/My Drive/AI700500_DL_Project/'\nWEIGHTDECAY = 1e-4\nMOMENTUM = 0.9\nBATCHSIZE = 64\nLR = 0.1\nEPOCHS = 150\nPRINTFREQ = 20","metadata":{"id":"Pv-hIWaJomEf"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Train Model","metadata":{"id":"9y7t4HTSm-9g"}},{"cell_type":"code","source":"import time\n\nimport torch\nimport torch.nn as nn\n\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data import Dataset, DataLoader\n\n\ndef main():\n model = resnet18()\n\n ##### optimizer / learning rate scheduler / criterion #####\n optimizer = torch.optim.SGD(model.parameters(), lr=LR,\n momentum=MOMENTUM, weight_decay=WEIGHTDECAY,\n nesterov=True)\n scheduler = torch.optim.lr_scheduler.MultiStepLR(optimizer, [75, 125],\n gamma=0.1)\n criterion = torch.nn.CrossEntropyLoss()\n ###########################################################\n\n model = model.cuda()\n criterion = criterion.cuda()\n\n # Check number of parameters your model\n pytorch_total_params = sum(p.numel() for p in model.parameters())\n print(f\"Number of parameters: {pytorch_total_params}\")\n\n normalize = transforms.Normalize(mean=[0.4686, 0.4408, 0.4006],\n std=[0.2722, 0.2646, 0.2743])\n train_transform = transforms.Compose([\n transforms.RandomResizedCrop(160),\n transforms.RandomHorizontalFlip(),\n transforms.ToTensor(),\n normalize,\n ])\n\n train_dataset = torchvision.datasets.ImageFolder(\n './Stanford_40_Actions/train', transform=train_transform)\n train_loader = DataLoader(train_dataset,\n batch_size=BATCHSIZE, shuffle=True,\n num_workers=4, pin_memory=True)\n\n last_top1_acc = 0\n for epoch in range(EPOCHS):\n print(\"\\n----- epoch: {}, lr: {} -----\".format(\n epoch, optimizer.param_groups[0][\"lr\"]))\n\n # train for one epoch\n start_time = time.time()\n last_top1_acc = train(train_loader, epoch, model, optimizer, criterion)\n elapsed_time = time.time() - start_time\n print('==> {:.2f} seconds to train this epoch\\n'.format(\n elapsed_time))\n\n # learning rate scheduling\n scheduler.step()\n\n # Save model each epoch\n torch.save(model.state_dict(), SAVEPATH+'model_weight.pth')\n\n print(f\"Last Top-1 Accuracy: {last_top1_acc}\")\n print(f\"Number of parameters: {pytorch_total_params}\")\n\n\n\ndef train(train_loader, epoch, model, optimizer, criterion):\n batch_time = AverageMeter('Time', ':6.3f')\n data_time = AverageMeter('Data', ':6.3f')\n losses = AverageMeter('Loss', ':.4e')\n top1 = AverageMeter('Acc@1', ':6.2f')\n top5 = AverageMeter('Acc@5', ':6.2f')\n progress = ProgressMeter(len(train_loader), batch_time, data_time, losses,\n top1, top5, prefix=\"Epoch: [{}]\".format(epoch))\n # switch to train mode\n model.train()\n\n end = time.time()\n for i, (input, target) in enumerate(train_loader):\n # measure data loading time\n data_time.update(time.time() - end)\n\n input = input.cuda()\n target = target.cuda()\n\n # compute output\n output = model(input)\n loss = criterion(output, target)\n\n # measure accuracy and record loss, accuracy \n acc1, acc5 = accuracy(output, target, topk=(1, 5))\n losses.update(loss.item(), input.size(0))\n top1.update(acc1[0].item(), input.size(0))\n top5.update(acc5[0].item(), input.size(0))\n\n # compute gradient and do SGD step\n optimizer.zero_grad()\n loss.backward()\n optimizer.step()\n\n # measure elapsed time\n batch_time.update(time.time() - end)\n end = time.time()\n\n if i % PRINTFREQ == 0:\n progress.print(i)\n\n print('=> Acc@1 {top1.avg:.3f} Acc@5 {top5.avg:.3f}'\n .format(top1=top1, top5=top5))\n return top1.avg\n\n\nif __name__ == \"__main__\":\n main()","metadata":{"id":"yiGordRmyP-E","outputId":"35788879-c6a0-46fb-a2ae-07d3e4a82e9d"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Make an evalutation csv file\n\nThis code makes an evaluation csv file for kaggle submission.\n\n**Never change below code!!!** (except test_loader setting)","metadata":{"id":"EMzXV6lTykgJ"}},{"cell_type":"code","source":"import torch\nimport pandas as pd\nimport argparse\nimport time\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data import Dataset, DataLoader\n\n\ndef eval():\n normalize = transforms.Normalize(mean=[0.4686, 0.4408, 0.4006],\n std=[0.2722, 0.2646, 0.2743])\n \n test_transform = transforms.Compose([\n transforms.Resize((160,160)),\n transforms.ToTensor(),\n normalize,\n ])\n\n test_dataset = torchvision.datasets.ImageFolder('./Stanford_40_Actions/test/', transform=test_transform)\n test_loader = DataLoader(test_dataset, batch_size=BATCHSIZE, num_workers=4, shuffle=False)\n\n model = resnet18()\n model = model.cuda()\n model.load_state_dict(torch.load(SAVEPATH+'model_weight.pth'))\n\n print('Make an evaluation csv file for kaggle submission...')\n Category = []\n for input, _ in test_loader:\n input = input.cuda()\n output = model(input)\n output = torch.argmax(output, dim=1)\n Category = Category + output.tolist()\n\n Id = list(range(0, 1410))\n samples = {\n 'Id': Id,\n 'Category': Category \n }\n df = pd.DataFrame(samples, columns=['Id', 'Category'])\n\n df.to_csv(SAVEPATH+'submission.csv', index=False)\n print('Done!!')\n\n\nif __name__ == \"__main__\":\n eval()","metadata":{"id":"MaUGSOCrAqx9","outputId":"4df399f4-44ba-4de7-dfab-14cb9d5fe4ed"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Upload your submission on kaggle\n\n1. Download the submission csv file \n\n\n2. Go to our kaggle submission link and click `Submit Predicitions` button \n\n\n3. Upload Submission `csv` file and click `make submission` button \n\n\n","metadata":{"id":"GxzbZmHfCVUe"}}]}