{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import pandas as pd\nimport tqdm\nimport time\nimport torchvision\nimport torch.nn as nn\nfrom tqdm import tqdm_notebook as tqdm\n\nfrom PIL import Image, ImageFile\nfrom torch.utils.data import Dataset\nimport torch\nimport torch.optim as optim\nfrom torchvision import transforms as T\nfrom torch.optim import lr_scheduler\nimport os\n\nprint(os.listdir(\"../input\"))\ndevice = torch.device(\"cuda:0\")","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"class RetinopathyDatasetTrain(Dataset):\n\n    def __init__(self, csv_file , transforms=None):\n\n        self.data = pd.read_csv(csv_file)\n        self.transform = transforms\n\n    def __len__(self):\n        return len(self.data)\n\n    def __getitem__(self, idx):\n        img_name = os.path.join('../input/train_images', self.data.loc[idx, 'id_code'] \n                                + '.png')\n        data = Image.open(img_name)\n        if self.transform:\n            data = self.transform(data)\n            \n        label =self.data.loc[idx, 'diagnosis']\n        return data,label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"transform = T.Compose([T.Resize(32),\n                      T.CenterCrop(32),\n                      T.ToTensor(),\n                      T.Normalize(mean=[0.5,0.5,0.5],std = [0.5,0.5,0.5])])\n\n\n\ntrain_dataset = RetinopathyDatasetTrain(csv_file='../input/train.csv',transforms=transform )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img,label= train_dataset[9]\nprint(img.size(),label)\n   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class RetinopathyDatasetTest(Dataset):\n\n    def __init__(self, csv_file , transforms=None):\n\n        self.data = pd.read_csv(csv_file)\n        self.transform = transforms\n\n    def __len__(self):\n        return len(self.data)\n\n    def __getitem__(self, idx):\n        img_name = os.path.join('../input/test_images', self.data.loc[idx, 'id_code'] \n                                + '.png')\n        data = Image.open(img_name)\n        if self.transform:\n            data = self.transform(data)\n            \n        return data\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dataset = RetinopathyDatasetTest(csv_file='../input/test.csv',transforms=transform )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgs= test_dataset[0]\nprint(imgs.size())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import math\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Bottleneck(nn.Module):\n    def __init__(self, in_planes, growth_rate):\n        super(Bottleneck, self).__init__()\n        self.bn1 = nn.BatchNorm2d(in_planes)\n        self.conv1 = nn.Conv2d(in_planes, 4*growth_rate, kernel_size=1, bias=False)\n        self.bn2 = nn.BatchNorm2d(4*growth_rate)\n        self.conv2 = nn.Conv2d(4*growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)\n\n    def forward(self, x):\n        out = self.conv1(F.relu(self.bn1(x)))\n        out = self.conv2(F.relu(self.bn2(out)))\n        out = torch.cat([out,x], 1)\n        return out\n\n\nclass Transition(nn.Module):\n    def __init__(self, in_planes, out_planes):\n        super(Transition, self).__init__()\n        self.bn = nn.BatchNorm2d(in_planes)\n        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=1, bias=False)\n\n    def forward(self, x):\n        out = self.conv(F.relu(self.bn(x)))\n        out = F.avg_pool2d(out, 2)\n        return out\n\n\nclass DenseNet(nn.Module):\n    def __init__(self, block, nblocks, growth_rate=12, reduction=0.5, num_classes=5):\n        super(DenseNet, self).__init__()\n        self.growth_rate = growth_rate\n\n        num_planes = 2*growth_rate\n        self.conv1 = nn.Conv2d(3, num_planes, kernel_size=3, padding=1, bias=False)\n\n        self.dense1 = self._make_dense_layers(block, num_planes, nblocks[0])\n        num_planes += nblocks[0]*growth_rate\n        out_planes = int(math.floor(num_planes*reduction))\n        self.trans1 = Transition(num_planes, out_planes)\n        num_planes = out_planes\n\n        self.dense2 = self._make_dense_layers(block, num_planes, nblocks[1])\n        num_planes += nblocks[1]*growth_rate\n        out_planes = int(math.floor(num_planes*reduction))\n        self.trans2 = Transition(num_planes, out_planes)\n        num_planes = out_planes\n\n        self.dense3 = self._make_dense_layers(block, num_planes, nblocks[2])\n        num_planes += nblocks[2]*growth_rate\n        out_planes = int(math.floor(num_planes*reduction))\n        self.trans3 = Transition(num_planes, out_planes)\n        num_planes = out_planes\n\n        self.dense4 = self._make_dense_layers(block, num_planes, nblocks[3])\n        num_planes += nblocks[3]*growth_rate\n\n        self.bn = nn.BatchNorm2d(num_planes)\n        self.linear = nn.Linear(num_planes, num_classes)\n\n    def _make_dense_layers(self, block, in_planes, nblock):\n        layers = []\n        for i in range(nblock):\n            layers.append(block(in_planes, self.growth_rate))\n            in_planes += self.growth_rate\n        return nn.Sequential(*layers)\n\n    def forward(self, x):\n        out = self.conv1(x)\n        out = self.trans1(self.dense1(out))\n        out = self.trans2(self.dense2(out))\n        out = self.trans3(self.dense3(out))\n        out = self.dense4(out)\n        out = F.avg_pool2d(F.relu(self.bn(out)), 4)\n        out = out.view(out.size(0), -1)\n        out = self.linear(out)\n        return out","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"net = DenseNet(Bottleneck, [6,12,24,16], growth_rate=32)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x = torch.randn(1,3,32,32)\ny = net(x)\nprint(y.size())\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(torch.cuda.is_available())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainloader = torch.utils.data.DataLoader(train_dataset, batch_size=32,\n                                          shuffle=True, num_workers=4)\n\ntestloader = torch.utils.data.DataLoader(test_dataset, batch_size=8, \n                                         shuffle=False, num_workers=4)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch.optim as optim\nnet=net.to(device)\ncriterion=nn.CrossEntropyLoss()\noptimizer=torch.optim.Adam(net.parameters(),lr=3e-04)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(device)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train(epoch):\n    print('\\nEpoch: %d' % epoch)\n    net.train()\n    train_loss = 0\n    correct = 0\n    total = 0\n    for batch_idx, (inputs, targets) in tqdm(enumerate(trainloader)):\n        inputs, targets = inputs.to(device), targets.to(device)\n        optimizer.zero_grad()\n        outputs = net(inputs)\n        loss = criterion(outputs, targets)\n        loss.backward()\n        optimizer.step()\n\n        train_loss += loss.item()\n        _, predicted = outputs.max(1)\n        total += targets.size(0)\n        correct += predicted.eq(targets).sum().item()\n\n        print(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'\n            % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for epoch in range(0,3):\n    train(epoch)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_preds10 = np.zeros((len(test_dataset), 1))\ndef test():\n    with torch.no_grad():\n        for batch_idx, inputs in tqdm(enumerate(testloader)):\n            inputs = inputs.to(device)\n            outputs = net(inputs)\n            _, predicted = outputs.max(1)\n            test_preds10[i * 8:(i + 1) * 8] = predicted.detach().cpu().squeeze().numpy().ravel().reshape(-1, 1)\n            \n            print(test_preds10[i * 8:(i + 1) * 8])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# test_data_loader = torch.utils.data.DataLoader(test_dataset, batch_size=32, shuffle=False, num_workers=4)\ntest()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(test_preds10.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv(\"../input/sample_submission.csv\")\nsample.diagnosis = test_preds10.astype(int)\nsample.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}