{"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":"Kaggle link: https://www.kaggle.com/c/dogs-vs-cats-redux-kernels-edition","metadata":{}},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-01-05T07:55:30.400580Z","iopub.execute_input":"2023-01-05T07:55:30.401515Z","iopub.status.idle":"2023-01-05T07:55:30.431995Z","shell.execute_reply.started":"2023-01-05T07:55:30.401414Z","shell.execute_reply":"2023-01-05T07:55:30.431109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Import everything needed","metadata":{}},{"cell_type":"code","source":"import zipfile\nimport glob\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nimport wandb\n\nfrom sklearn.model_selection import train_test_split\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader, Dataset\nfrom torchvision import datasets, transforms\nnp.random.seed(0)\ntorch.manual_seed(0)\ntorch.cuda.manual_seed(0)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:30.435203Z","iopub.execute_input":"2023-01-05T07:55:30.435477Z","iopub.status.idle":"2023-01-05T07:55:34.378536Z","shell.execute_reply.started":"2023-01-05T07:55:30.435452Z","shell.execute_reply":"2023-01-05T07:55:34.377280Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Unzip datasets","metadata":{}},{"cell_type":"code","source":"train_dir = 'train'\ntest_dir = 'test'\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip') as train_zip:\n    train_zip.extractall('')\n    \nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip') as test_zip:\n    test_zip.extractall('')\ntrain_list = glob.glob(os.path.join(train_dir,'*.jpg'))\ntest_list = glob.glob(os.path.join(test_dir, '*.jpg'))\nprint(f\"Train Data: {len(train_list)}\")\nprint(f\"Test Data: {len(test_list)}\")","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:34.384409Z","iopub.execute_input":"2023-01-05T07:55:34.385476Z","iopub.status.idle":"2023-01-05T07:55:52.845476Z","shell.execute_reply.started":"2023-01-05T07:55:34.385438Z","shell.execute_reply":"2023-01-05T07:55:52.844465Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = [path.split('/')[-1].split('.')[0] for path in train_list]","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:52.847003Z","iopub.execute_input":"2023-01-05T07:55:52.847590Z","iopub.status.idle":"2023-01-05T07:55:52.864089Z","shell.execute_reply.started":"2023-01-05T07:55:52.847552Z","shell.execute_reply":"2023-01-05T07:55:52.863122Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plot random image with their label","metadata":{}},{"cell_type":"code","source":"random_idx = np.random.randint(1, len(train_list), size=9)\nfig, axes = plt.subplots(3, 3, figsize=(16, 12))\n\nfor idx, ax in enumerate(axes.ravel()):\n    img = Image.open(train_list[idx])\n    ax.set_title(labels[idx])\n    ax.imshow(img)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:52.867541Z","iopub.execute_input":"2023-01-05T07:55:52.867895Z","iopub.status.idle":"2023-01-05T07:55:54.352917Z","shell.execute_reply.started":"2023-01-05T07:55:52.867870Z","shell.execute_reply":"2023-01-05T07:55:54.351925Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Use Sklearn to split data","metadata":{}},{"cell_type":"code","source":"train_list, valid_list = train_test_split(train_list, \n                                          test_size=0.2,\n                                          stratify=labels,\n                                          random_state=0)\nprint(f\"Train Data: {len(train_list)}\")\nprint(f\"Validation Data: {len(valid_list)}\")\nprint(f\"Test Data: {len(test_list)}\")","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.353872Z","iopub.execute_input":"2023-01-05T07:55:54.354190Z","iopub.status.idle":"2023-01-05T07:55:54.387790Z","shell.execute_reply.started":"2023-01-05T07:55:54.354160Z","shell.execute_reply":"2023-01-05T07:55:54.386857Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We will discuss this in more detail in a near future...","metadata":{}},{"cell_type":"code","source":"train_transforms = transforms.Compose([\n        transforms.Resize(128), # makes it easier for the GPU\n        transforms.RandomResizedCrop(112),\n        transforms.RandomHorizontalFlip(),\n        transforms.ToTensor()])\n\nval_transforms = transforms.Compose([\n        transforms.Resize(128),\n        transforms.CenterCrop(112),\n        transforms.ToTensor()])\n\n\ntest_transforms = transforms.Compose([\n        transforms.Resize(128),\n        transforms.CenterCrop(112),\n        transforms.ToTensor()])","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.389676Z","iopub.execute_input":"2023-01-05T07:55:54.390137Z","iopub.status.idle":"2023-01-05T07:55:54.398396Z","shell.execute_reply.started":"2023-01-05T07:55:54.390092Z","shell.execute_reply":"2023-01-05T07:55:54.397313Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Define the dataset using PIL to read image","metadata":{}},{"cell_type":"code","source":"class CatsDogsDataset(Dataset):\n    def __init__(self, file_list, transform=None, use_gpu=torch.cuda.is_available(), test=False):\n        self.file_list = file_list\n        self.transform = transform\n        self.filelength = len(file_list)\n        self.use_gpu = use_gpu\n        self.test = test\n\n    def __len__(self):\n        return self.filelength\n\n    def __getitem__(self, idx):\n        img_path = self.file_list[idx]\n        img = Image.open(img_path)\n        img_transformed = self.transform(img)\n        label = img_path.split(\"/\")[-1].split(\".\")[0]\n        if not self.test:\n            label = 1 if label == \"dog\" else 0\n        else:\n            label = int(label)\n        label = torch.tensor(label)\n        if self.use_gpu:\n            img_transformed = img_transformed.cuda()\n            label = label.cuda()\n        return img_transformed, label","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.399884Z","iopub.execute_input":"2023-01-05T07:55:54.400429Z","iopub.status.idle":"2023-01-05T07:55:54.623001Z","shell.execute_reply.started":"2023-01-05T07:55:54.400390Z","shell.execute_reply":"2023-01-05T07:55:54.622003Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = CatsDogsDataset(train_list, transform=train_transforms)\nvalid_data = CatsDogsDataset(valid_list, transform=val_transforms)\ntest_data = CatsDogsDataset(test_list, transform=test_transforms, test=True)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.624450Z","iopub.execute_input":"2023-01-05T07:55:54.624796Z","iopub.status.idle":"2023-01-05T07:55:54.629590Z","shell.execute_reply.started":"2023-01-05T07:55:54.624762Z","shell.execute_reply":"2023-01-05T07:55:54.628661Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Create dataloader, you can modify the batch size if needed","metadata":{}},{"cell_type":"code","source":"batch_size = 32\ntrain_loader = DataLoader(dataset=train_data, batch_size=batch_size, shuffle=True)\nvalid_loader = DataLoader(dataset=valid_data, batch_size=batch_size, shuffle=False)\ntest_loader = DataLoader(dataset=test_data, batch_size=batch_size, shuffle=False)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.631128Z","iopub.execute_input":"2023-01-05T07:55:54.632238Z","iopub.status.idle":"2023-01-05T07:55:54.643766Z","shell.execute_reply.started":"2023-01-05T07:55:54.632203Z","shell.execute_reply":"2023-01-05T07:55:54.642745Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"### CNN Model","metadata":{}},{"cell_type":"code","source":"def init_my_layer(m, typ=\"xavier\",gain=1):\n    if typ == \"xavier\":\n        torch.nn.init.xavier_normal_(m.weight, gain)\n    elif typ == \"kaiming\":\n        torch.nn.init.kaiming_normal_(m.weight)\n    torch.nn.init.constant_(m.bias, 0)\n    return m","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.649610Z","iopub.execute_input":"2023-01-05T07:55:54.649893Z","iopub.status.idle":"2023-01-05T07:55:54.657774Z","shell.execute_reply.started":"2023-01-05T07:55:54.649869Z","shell.execute_reply":"2023-01-05T07:55:54.656813Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Residual(nn.Module):\n    def __init__(self, input_channels, num_channels, use_1x1conv=False, strides=1):\n        super().__init__()\n        self.conv1 = nn.Conv2d(input_channels, num_channels, kernel_size=3,\n                               padding=1, stride=strides)\n        self.conv2 = nn.Conv2d(num_channels, num_channels, kernel_size=3,\n                               padding=1)\n        if use_1x1conv:\n            self.conv3 = nn.Conv2d(input_channels, num_channels,\n                                   kernel_size=1, stride=strides)\n        else:\n            self.conv3 = None\n        self.bn1 = nn.BatchNorm2d(num_channels)\n        self.bn2 = nn.BatchNorm2d(num_channels)\n\n    def forward(self, X):\n        Y = F.relu(self.bn1(self.conv1(X)))\n        Y = self.bn2(self.conv2(Y))\n        if self.conv3:\n            X = self.conv3(X)\n        Y += X\n        return F.relu(Y)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.661323Z","iopub.execute_input":"2023-01-05T07:55:54.661654Z","iopub.status.idle":"2023-01-05T07:55:54.671164Z","shell.execute_reply.started":"2023-01-05T07:55:54.661626Z","shell.execute_reply":"2023-01-05T07:55:54.670262Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def resnet_block(input_channels, num_channels, num_residuals):\n    blk = []\n    for i in range(num_residuals):\n        if i == 0 and input_channels != num_channels: # 1x1 applied only once per block if needed\n            blk.append(\n                Residual(input_channels, num_channels, use_1x1conv=True,\n                         strides=2))\n        else:\n            blk.append(Residual(num_channels, num_channels))\n    return blk\n\nb1 = nn.Sequential(nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3),\n                              nn.BatchNorm2d(64), nn.ReLU(),\n                              nn.MaxPool2d(kernel_size=3, stride=2, padding=1))\nb2 = nn.Sequential(*resnet_block(64, 64, 2))\nb3 = nn.Sequential(*resnet_block(64, 128, 2))\nb4 = nn.Sequential(*resnet_block(128, 256, 2))\nb5 = nn.Sequential(*resnet_block(256, 512, 2))","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.672418Z","iopub.execute_input":"2023-01-05T07:55:54.672860Z","iopub.status.idle":"2023-01-05T07:55:54.794229Z","shell.execute_reply.started":"2023-01-05T07:55:54.672784Z","shell.execute_reply":"2023-01-05T07:55:54.793172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Net3(nn.Module):    \n    def __init__(self):\n        super(Net3, self).__init__()\n        self.conv1 = nn.Conv2d(3, 16, 5)\n        self.conv2 = nn.Conv2d(16, 32, 5)\n        self.conv3 = nn.Conv2d(32, 64, 5)\n        self.fc1 = init_my_layer(nn.Linear(256, 500), typ=\"kaiming\")\n        self.fc2 = init_my_layer(nn.Linear(500, 250), typ=\"kaiming\")\n        self.fc3 = init_my_layer(nn.Linear(250, 1))\n\n        self.max_pool = nn.MaxPool2d(kernel_size=3)\n        self.dropout = nn.Dropout(p=0.2)\n        self.sigmoid = nn.Sigmoid()\n\n    def forward(self, x):\n        x = self.max_pool(F.relu(self.conv1(x)))\n        x = self.max_pool(F.relu(self.conv2(x)))\n        x = self.max_pool(F.relu(self.conv3(x)))\n        x = x.reshape(x.size(0), -1)\n        x = self.dropout(F.relu(self.fc1(x)))\n        x = self.dropout(F.relu(self.fc2(x)))\n        x = self.fc3(x)\n        return self.sigmoid(x)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.795589Z","iopub.execute_input":"2023-01-05T07:55:54.796058Z","iopub.status.idle":"2023-01-05T07:55:54.808168Z","shell.execute_reply.started":"2023-01-05T07:55:54.796023Z","shell.execute_reply":"2023-01-05T07:55:54.807184Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Net2(nn.Module):    \n    def __init__(self):\n        super(Net2, self).__init__()\n        self.conv1 = nn.Conv2d(3, 16, 5)\n        self.conv2 = nn.Conv2d(16, 32, 5)\n        self.conv3 = nn.Conv2d(32, 64, 5)\n        self.fc1 = init_my_layer(nn.Linear(256, 500), typ=\"kaiming\")\n        self.fc2 = init_my_layer(nn.Linear(500, 50), typ=\"kaiming\")\n        self.fc3 = init_my_layer(nn.Linear(50, 2))\n\n        self.max_pool = nn.MaxPool2d(kernel_size=3)\n        self.dropout = nn.Dropout(p=0.2)\n        self.logsoftmax = nn.LogSoftmax(dim=1)\n\n    def forward(self, x):\n        x = self.max_pool(F.relu(self.conv1(x)))\n        x = self.max_pool(F.relu(self.conv2(x)))\n        x = self.max_pool(F.relu(self.conv3(x)))\n        x = x.reshape(x.size(0), -1)\n        x = self.dropout(F.relu(self.fc1(x)))\n        x = self.dropout(F.relu(self.fc2(x)))\n        x = self.fc3(x)\n        return x","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.810676Z","iopub.execute_input":"2023-01-05T07:55:54.811444Z","iopub.status.idle":"2023-01-05T07:55:54.822347Z","shell.execute_reply.started":"2023-01-05T07:55:54.811400Z","shell.execute_reply":"2023-01-05T07:55:54.821402Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class Net(nn.Module):    \n    def __init__(self):\n        super(Net, self).__init__()\n        self.conv1 = nn.Conv2d(3, 96, 5)\n        self.conv2 = nn.Conv2d(96, 256, 5)\n        self.fc1 = init_my_layer(nn.Linear(25600, 1024), typ=\"kaiming\")\n        self.fc2 = init_my_layer(nn.Linear(1024, 256), typ=\"kaiming\")\n        self.fc3 = init_my_layer(nn.Linear(256, 2))\n\n        self.max_pool = nn.MaxPool2d(kernel_size=3)\n        self.dropout = nn.Dropout(p=0.2)\n        self.logsoftmax = nn.LogSoftmax(dim=1)\n\n    def forward(self, x):\n        x = self.max_pool(F.relu(self.conv1(x)))\n        # print(x.size())\n        x = self.max_pool(F.relu(self.conv2(x)))\n        x = x.reshape(x.size(0), -1)\n        x = self.dropout(F.relu(self.fc1(x)))\n        x = self.dropout(F.relu(self.fc2(x)))\n        x = self.fc3(x)\n        return self.logsoftmax(x)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.823922Z","iopub.execute_input":"2023-01-05T07:55:54.824296Z","iopub.status.idle":"2023-01-05T07:55:54.837783Z","shell.execute_reply.started":"2023-01-05T07:55:54.824261Z","shell.execute_reply":"2023-01-05T07:55:54.836696Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"class LeNet(nn.Module):    \n    def __init__(self):\n        super(LeNet, self).__init__()\n        #TODO\n        self.conv1 = nn.Conv2d(3, 6, 5)\n        self.conv2 = nn.Conv2d(6, 16, 5)\n        self.fc1 = init_my_layer(nn.Linear(10000, 120),typ=\"kaiming\")\n        self.fc2 = init_my_layer(nn.Linear(120, 84),typ=\"kaiming\")\n        self.fc3 = init_my_layer(nn.Linear(84, 2))\n        self.max_pool = nn.MaxPool2d(kernel_size=2)\n        self.softmax = nn.Softmax(dim=1)\n\n    def forward(self, x):\n        #TODO\n        x = self.max_pool(F.relu(self.conv1(x)))\n        x = self.max_pool(F.relu(self.conv2(x)))\n        x = x.reshape(x.size(0), -1)\n        x = F.relu(self.fc1(x))\n        x = F.relu(self.fc2(x))\n        return self.fc3(x)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.840048Z","iopub.execute_input":"2023-01-05T07:55:54.840770Z","iopub.status.idle":"2023-01-05T07:55:54.850141Z","shell.execute_reply.started":"2023-01-05T07:55:54.840733Z","shell.execute_reply":"2023-01-05T07:55:54.848882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# net = LeNet()\n# net = Net2()\n# net = Net()\n# net = Net3()\nnet = nn.Sequential(b1, b2, b3, b4, b5, nn.AdaptiveAvgPool2d((1, 1)),\n                    nn.Flatten(), nn.Linear(512, 1), nn.Sigmoid())\nif torch.cuda.is_available():\n    net = net.to('cuda')","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:54.851708Z","iopub.execute_input":"2023-01-05T07:55:54.852070Z","iopub.status.idle":"2023-01-05T07:55:58.072233Z","shell.execute_reply.started":"2023-01-05T07:55:54.852037Z","shell.execute_reply":"2023-01-05T07:55:58.071086Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"num_epochs = 30\nlr = 1e-3\nmomentum = 0.9\n\nwandb.init(project='CATvsDOG_CNN', save_code=True, config={\"nb_epoch\":num_epochs,\"lr\":lr, \"momentum\":momentum})\n\n# loss = nn.CrossEntropyLoss() # with others\n# loss = nn.NLLLoss() # with logsoftmax\nloss = nn.BCELoss() # with sigmoid\n\noptimizer = torch.optim.SGD(net.parameters(), lr=lr, momentum=momentum)\n\nfor epoch in range(num_epochs):\n    train_loss = 0\n    val_loss = 0\n    nb_true_pred = 0\n    net.train() # Important\n    for X, y in train_loader:\n#         if torch.cuda.is_available():\n#             X = X.to('cuda')\n#             y = y.to('cuda')\n        pred = net(X)\n        training_loss = loss(pred.flatten(), y.float())\n        optimizer.zero_grad()\n        training_loss.backward()\n        optimizer.step()\n#         _, predicted = torch.max(pred, dim=1)\n        predicted = torch.ge(pred.flatten(), 0.5)\n        nb_true_pred += len(y[y == predicted])\n        train_loss += training_loss\n    with torch.no_grad():\n        net.eval() # Important\n        nb_true_pred_val = 0\n        for X, y in valid_loader:\n#             if torch.cuda.is_available():\n#                 X = X.to('cuda')\n#                 y = y.to('cuda')\n            pred = net(X)\n            validation_loss = loss(pred.flatten(), y.float())\n#             _,pred_value = torch.max(pred, dim=1)\n            pred_value = torch.ge(pred.flatten(), 0.5)\n            nb_true_pred_val += len(y[y == pred_value])\n            val_loss += validation_loss\n         \n    accuracy = nb_true_pred / len(train_data)\n    accuracy_val = nb_true_pred_val / len(valid_data)\n    wandb.log({'training/loss': train_loss.item(), 'training/accuracy': accuracy,'validation/loss': val_loss, 'validation/accuracy': accuracy_val})\n\n    print(f'epoch {epoch + 1}, loss {train_loss.item()}')\n    print(f'Accuracy: {accuracy}')\ntorch.save(net.state_dict(), 'catdog_cnn.pt')","metadata":{"execution":{"iopub.status.busy":"2023-01-05T07:55:58.073771Z","iopub.execute_input":"2023-01-05T07:55:58.075263Z","iopub.status.idle":"2023-01-05T08:55:46.731761Z","shell.execute_reply.started":"2023-01-05T07:55:58.075218Z","shell.execute_reply":"2023-01-05T08:55:46.730721Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"with torch.no_grad():\n    net.eval()\n    test_pred = torch.LongTensor()\n    result_dict = []\n    for i, data in enumerate(test_loader):\n        x, y = data\n        output = net(x)\n        predicted = output.cpu()\n        predicted = torch.where(predicted > 0.5, torch.ones_like(predicted), torch.zeros_like(predicted))\n        for i in range(len(y)):\n            result_dict.append({'id': y[i].cpu().item(), 'label': predicted[i].item()})\n    out_df = pd.DataFrame(result_dict)\n    out_df.to_csv('submission.csv', index=False)\n    print(out_df)","metadata":{"execution":{"iopub.status.busy":"2023-01-05T08:55:46.733519Z","iopub.execute_input":"2023-01-05T08:55:46.734190Z","iopub.status.idle":"2023-01-05T08:56:37.902424Z","shell.execute_reply.started":"2023-01-05T08:55:46.734153Z","shell.execute_reply":"2023-01-05T08:56:37.901453Z"},"trusted":true},"execution_count":null,"outputs":[]}]}