{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":29653,"databundleVersionId":2420395,"sourceType":"competition"}],"dockerImageVersionId":30699,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-05-22T02:25:15.707266Z","iopub.execute_input":"2024-05-22T02:25:15.707544Z","iopub.status.idle":"2024-05-22T02:25:21.095145Z","shell.execute_reply.started":"2024-05-22T02:25:15.707520Z","shell.execute_reply":"2024-05-22T02:25:21.093837Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nimport glob\nimport time\nimport random\n\nimport numpy as np\nimport pandas as pd\n\nimport pydicom\nfrom pydicom.pixel_data_handlers.util import apply_voi_lut\nimport cv2\nimport matplotlib.pyplot as plt\n\nimport torch\nfrom torch import nn\nfrom torch.utils import data as torch_data\nfrom torch.nn import functional as F\nfrom torch.utils.data import Dataset, DataLoader\nimport torchvision.models as models","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:30.377892Z","iopub.execute_input":"2024-05-22T02:36:30.378550Z","iopub.status.idle":"2024-05-22T02:36:30.385832Z","shell.execute_reply.started":"2024-05-22T02:36:30.378519Z","shell.execute_reply":"2024-05-22T02:36:30.383957Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install efficientnet_pytorch","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:35:31.286568Z","iopub.execute_input":"2024-05-22T02:35:31.287161Z","iopub.status.idle":"2024-05-22T02:35:43.742743Z","shell.execute_reply.started":"2024-05-22T02:35:31.287134Z","shell.execute_reply":"2024-05-22T02:35:43.741623Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import efficientnet_pytorch\n\nfrom sklearn.model_selection import StratifiedKFold\n\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nseed = 123","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:32.097807Z","iopub.execute_input":"2024-05-22T02:36:32.098159Z","iopub.status.idle":"2024-05-22T02:36:32.103989Z","shell.execute_reply.started":"2024-05-22T02:36:32.098131Z","shell.execute_reply":"2024-05-22T02:36:32.102732Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def seed_everything(seed):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = True\n\n\nseed_everything(seed)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:33.344484Z","iopub.execute_input":"2024-05-22T02:36:33.345490Z","iopub.status.idle":"2024-05-22T02:36:33.351269Z","shell.execute_reply.started":"2024-05-22T02:36:33.345451Z","shell.execute_reply":"2024-05-22T02:36:33.350287Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Model","metadata":{}},{"cell_type":"code","source":"class CFG:\n    img_size = 256\n    n_frames = 10\n\n    cnn_features = 256\n    lstm_hidden = 32\n\n    n_fold = 5\n    n_epochs = 15\n\nclass CNN(nn.Module):\n    def __init__(self):\n        super().__init__()\n        self.map = nn.Conv2d(in_channels=4, out_channels=1, kernel_size=1)\n        self.map1 = nn.Conv2d(in_channels=4, out_channels=1, kernel_size=1)\n        self.map2 = nn.Conv2d(in_channels=4, out_channels=1, kernel_size=1)\n        self.map3 = nn.Conv2d(in_channels=4, out_channels=1, kernel_size=1)\n        self.FT = nn.Conv2d(in_channels=4, out_channels=3, kernel_size=1)\n        # self.net = efficientnet_pytorch.EfficientNet.from_name(\"efficientnet-b0\")\n        # checkpoint = torch.load(\"./input/efficientnet-pytorch/efficientnet-b0-08094119.pth\")\n        # self.net.load_state_dict(checkpoint)\n        self.net = models.resnet34(pretrained=False)\n        n_features = self.net.fc.in_features\n        self.net.fc = nn.Linear(in_features=n_features, out_features=CFG.cnn_features, bias=True)\n\n    def forward(self, x):\n        x1 = F.relu(self.map(x))\n        x2 = F.relu(self.map1(x))\n        x3 = F.relu(self.map2(x))\n        x4 = F.relu(self.map3(x))\n        x_cat = torch.cat((x1, x2, x3, x4), dim=1)\n        net_in = F.relu(self.FT(x_cat))\n        out = self.net(net_in)\n        return out\n\n\nclass Model(nn.Module):\n    def __init__(self):\n        super(Model, self).__init__()\n        self.cnn = CNN()\n        self.rnn = nn.LSTM(CFG.cnn_features, CFG.lstm_hidden, 2, batch_first=True)\n        self.fc = nn.Linear(CFG.lstm_hidden, 1, bias=True)\n\n    def forward(self, x):\n        # x shape: BxTxCxHxW\n        batch_size, timesteps, C, H, W = x.size()\n        c_in = x.view(batch_size * timesteps, C, H, W)\n        c_out = self.cnn(c_in)\n        r_in = c_out.view(batch_size, timesteps, -1)\n        output, (hn, cn) = self.rnn(r_in)\n\n        out = self.fc(hn[-1])\n        return out","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:34.452518Z","iopub.execute_input":"2024-05-22T02:36:34.453155Z","iopub.status.idle":"2024-05-22T02:36:34.468008Z","shell.execute_reply.started":"2024-05-22T02:36:34.453121Z","shell.execute_reply":"2024-05-22T02:36:34.467079Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"# Load dataset","metadata":{}},{"cell_type":"code","source":"def load_image(path):\n    image = cv2.imread(path, 0)\n    if image is None:\n        return np.zeros((CFG.img_size, CFG.img_size))\n\n    image = cv2.resize(image, (CFG.img_size, CFG.img_size)) / 255\n    return image.astype('f')\n\n\ndef uniform_temporal_subsample(x, num_samples):\n    '''\n        Moddified from https://github.com/facebookresearch/pytorchvideo/blob/d7874f788bc00a7badfb4310a912f6e531ffd6d3/pytorchvideo/transforms/functional.py#L19\n        Args:\n            x: input list\n            num_samples: The number of equispaced samples to be selected\n        Returns:\n            Output list\n    '''\n    t = len(x)\n    indices = torch.linspace(0, t - 1, num_samples)\n    indices = torch.clamp(indices, 0, t - 1).long()\n    return [x[i] for i in indices]\n\n\nclass DataRetriever(Dataset):\n    def __init__(self, paths, targets, transform=None):\n        self.paths = paths\n        self.targets = targets\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.paths)\n\n    def read_video(self, vid_paths):\n        video = [load_image(path) for path in vid_paths]\n        #  import pdb;pdb.set_trace()\n        if self.transform:\n            seed = random.randint(0, 99999)\n            for i in range(len(video)):\n                random.seed(seed)\n                video[i] = self.transform(image=video[i])[\"image\"]\n\n        video = [torch.tensor(frame, dtype=torch.float32) for frame in video]\n        if len(video) == 0:\n            video = torch.zeros(CFG.n_frames, CFG.img_size, CFG.img_size)\n        else:\n            video = torch.stack(video)  # T * C * H * W\n        #         video = torch.transpose(video, 0, 1) # C * T * H * W\n        return video\n\n    def __getitem__(self, index):\n        _id = self.paths[index]\n        patient_path = f\"./input/rsna-miccai-png/train/{str(_id).zfill(5)}/\"\n        channels = []\n        for t in [\"FLAIR\", \"T1w\", \"T1wCE\", \"T2w\"]:\n            t_paths = sorted(\n                glob.glob(os.path.join(patient_path, t, \"*\")),\n                key=lambda x: int(x[:-4].split(\"-\")[-1]),\n            )\n            num_samples = CFG.n_frames\n            if len(t_paths) < num_samples:\n                in_frames_path = t_paths\n            else:\n                in_frames_path = uniform_temporal_subsample(t_paths, num_samples)\n\n            channel = self.read_video(in_frames_path)\n            if channel.shape[0] == 0:\n                print(\"1 channel empty\")\n                channel = torch.zeros(num_samples, CFG.img_size, CFG.img_size)\n            channels.append(channel)\n\n        channels = torch.stack(channels).transpose(0, 1)\n\n        y = torch.tensor(self.targets[index], dtype=torch.float)\n        return {\"X\": channels.float(), \"y\": y}\n\ndf = pd.read_csv(\"/kaggle/input/rsna-miccai-brain-tumor-radiogenomic-classification/train_labels.csv\")","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:35.288551Z","iopub.execute_input":"2024-05-22T02:36:35.289210Z","iopub.status.idle":"2024-05-22T02:36:35.310625Z","shell.execute_reply.started":"2024-05-22T02:36:35.289177Z","shell.execute_reply":"2024-05-22T02:36:35.309740Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import albumentations as A\nfrom albumentations.pytorch import ToTensorV2\n\ntrain_transform = A.Compose([\n                                A.HorizontalFlip(p=0.5),\n                                A.ShiftScaleRotate(\n                                    shift_limit=0.0625,\n                                    scale_limit=0.1,\n                                    rotate_limit=10,\n                                    p=0.5\n                                ),\n                                A.RandomBrightnessContrast(p=0.5),\n                            ])\nvalid_transform = A.Compose([\n                            ])\n\n\nclass LossMeter:\n    def __init__(self):\n        self.avg = 0\n        self.n = 0\n\n    def update(self, val):\n        self.n += 1\n        # incremental update\n        self.avg = val / self.n + (self.n - 1) / self.n * self.avg\n\n\nclass AccMeter:\n    def __init__(self):\n        self.avg = 0\n        self.n = 0\n\n    def update(self, y_true, y_pred):\n        y_true = y_true.cpu().numpy().astype(int)\n        y_pred = y_pred.cpu().numpy() >= 0\n        last_n = self.n\n        self.n += len(y_true)\n        true_count = np.sum(y_true == y_pred)\n        # incremental update\n        self.avg = true_count / self.n + last_n / self.n * self.avg\n\n\nclass Trainer:\n    def __init__(\n            self,\n            model,\n            device,\n            optimizer,\n            criterion,\n            loss_meter,\n            score_meter\n    ):\n        self.model = model\n        self.device = device\n        self.optimizer = optimizer\n        self.criterion = criterion\n        self.loss_meter = loss_meter\n        self.score_meter = score_meter\n        self.hist = {'val_loss': [],\n                     'val_score': [],\n                     'train_loss': [],\n                     'train_score': []\n                     }\n\n        self.best_valid_score = -np.inf\n        self.best_valid_loss = np.inf\n        self.n_patience = 0\n\n        self.messages = {\n            \"epoch\": \"[Epoch {}: {}] loss: {:.5f}, score: {:.5f}, time: {} s\",\n            \"checkpoint\": \"The score improved from {:.5f} to {:.5f}. Save model to '{}'\",\n            \"patience\": \"\\nValid score didn't improve last {} epochs.\"\n        }\n\n    def fit(self, epochs, train_loader, valid_loader, save_path, patience):\n        for n_epoch in range(1, epochs + 1):\n            self.info_message(\"EPOCH: {}\", n_epoch)\n\n            train_loss, train_score, train_time = self.train_epoch(train_loader)\n            valid_loss, valid_score, valid_time = self.valid_epoch(valid_loader)\n            self.hist['val_loss'].append(valid_loss)\n            self.hist['train_loss'].append(train_loss)\n            self.hist['val_score'].append(valid_score)\n            self.hist['train_score'].append(train_score)\n\n            self.info_message(\n                self.messages[\"epoch\"], \"Train\", n_epoch, train_loss, train_score, train_time\n            )\n\n            self.info_message(\n                self.messages[\"epoch\"], \"Valid\", n_epoch, valid_loss, valid_score, valid_time\n            )\n\n            if self.best_valid_score < valid_score:\n                self.info_message(\n                    self.messages[\"checkpoint\"], self.best_valid_score, valid_score, save_path\n                )\n                self.best_valid_score = valid_score\n                self.best_valid_loss = valid_loss\n                self.save_model(n_epoch, save_path)\n                self.n_patience = 0\n            else:\n                self.n_patience += 1\n\n            if self.n_patience >= patience:\n                self.info_message(self.messages[\"patience\"], patience)\n                break\n\n        return self.best_valid_loss, self.best_valid_score\n\n    def train_epoch(self, train_loader):\n        self.model.train()\n        t = time.time()\n        train_loss = self.loss_meter()\n        train_score = self.score_meter()\n\n        for step, batch in enumerate(train_loader, 1):\n            X = batch[\"X\"].to(self.device)\n            targets = batch[\"y\"].to(self.device)\n            self.optimizer.zero_grad()\n            outputs = self.model(X).squeeze(1)\n\n            loss = self.criterion(outputs, targets)\n            loss.backward()\n\n            train_loss.update(loss.detach().item())\n            train_score.update(targets, outputs.detach())\n\n            self.optimizer.step()\n\n            _loss, _score = train_loss.avg, train_score.avg\n            message = 'Train Step {}/{}, train_loss: {:.5f}, train_score: {:.5f}'\n            self.info_message(message, step, len(train_loader), _loss, _score, end=\"\\r\")\n\n        return train_loss.avg, train_score.avg, int(time.time() - t)\n\n    def valid_epoch(self, valid_loader):\n        self.model.eval()\n        t = time.time()\n        valid_loss = self.loss_meter()\n        valid_score = self.score_meter()\n\n        for step, batch in enumerate(valid_loader, 1):\n            with torch.no_grad():\n                X = batch[\"X\"].to(self.device)\n                targets = batch[\"y\"].to(self.device)\n\n                outputs = self.model(X).squeeze(1)\n                loss = self.criterion(outputs, targets)\n\n                valid_loss.update(loss.detach().item())\n                valid_score.update(targets, outputs)\n\n            _loss, _score = valid_loss.avg, valid_score.avg\n            message = 'Valid Step {}/{}, valid_loss: {:.5f}, valid_score: {:.5f}'\n            self.info_message(message, step, len(valid_loader), _loss, _score, end=\"\\r\")\n\n        return valid_loss.avg, valid_score.avg, int(time.time() - t)\n\n    def plot_loss(self):\n        plt.title(\"Loss\")\n        plt.xlabel(\"Training Epochs\")\n        plt.ylabel(\"Loss\")\n\n        plt.plot(self.hist['train_loss'], label=\"Train\")\n        plt.plot(self.hist['val_loss'], label=\"Validation\")\n        plt.legend()\n        plt.show()\n\n    def plot_score(self):\n        plt.title(\"Score\")\n        plt.xlabel(\"Training Epochs\")\n        plt.ylabel(\"Acc\")\n\n        plt.plot(self.hist['train_score'], label=\"Train\")\n        plt.plot(self.hist['val_score'], label=\"Validation\")\n        plt.legend()\n        plt.show()\n\n    def save_model(self, n_epoch, save_path):\n        torch.save(\n            {\n                \"model_state_dict\": self.model.state_dict(),\n                \"optimizer_state_dict\": self.optimizer.state_dict(),\n                \"best_valid_score\": self.best_valid_score,\n                \"n_epoch\": n_epoch,\n            },\n            save_path,\n        )\n\n    @staticmethod\n    def info_message(message, *args, end=\"\\n\"):\n        print(message.format(*args), end=end)\n","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:35.895982Z","iopub.execute_input":"2024-05-22T02:36:35.896306Z","iopub.status.idle":"2024-05-22T02:36:35.929432Z","shell.execute_reply.started":"2024-05-22T02:36:35.896281Z","shell.execute_reply":"2024-05-22T02:36:35.928528Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"skf = StratifiedKFold(n_splits=CFG.n_fold)\nt = df['MGMT_value']\n\nstart_time = time.time()\n\nlosses = []\nscores = []\nsave_path = './save_models/'\nos.makedirs(save_path, exist_ok=True)\nfor fold, (train_index, val_index) in enumerate(skf.split(np.zeros(len(t)), t), 1):\n    print('-' * 30)\n    print(f\"Fold {fold}\")\n\n    train_df = df.loc[train_index]\n    val_df = df.loc[val_index]\n    train_retriever = DataRetriever(\n        train_df[\"BraTS21ID\"].values,\n        train_df[\"MGMT_value\"].values,\n        train_transform\n    )\n    val_retriever = DataRetriever(\n        val_df[\"BraTS21ID\"].values,\n        val_df[\"MGMT_value\"].values\n    )\n    train_loader = torch_data.DataLoader(\n        train_retriever,\n        batch_size=8,\n        shuffle=True,\n        num_workers=0,\n    )\n    valid_loader = torch_data.DataLoader(\n        val_retriever,\n        batch_size=8,\n        shuffle=False,\n        num_workers=0,\n    )\n\n    model = Model()\n    model.to(device)\n\n    optimizer = torch.optim.Adam(model.parameters(), lr=0.0001)\n    criterion = F.binary_cross_entropy_with_logits\n\n    trainer = Trainer(\n        model,\n        device,\n        optimizer,\n        criterion,\n        LossMeter,\n        AccMeter\n    )\n    loss, score = trainer.fit(\n        CFG.n_epochs,\n        train_loader,\n        valid_loader,\n        save_path+f\"best-model-{fold}.pth\",\n        100,\n    )\n    losses.append(loss)\n    scores.append(score)\n\n    trainer.plot_loss()\n    trainer.plot_score()\n\nelapsed_time = time.time() - start_time\nprint('\\nTraining complete in {:.0f}m {:.0f}s'.format(elapsed_time // 60, elapsed_time % 60))\nprint('Avg loss {}'.format(np.mean(losses)))\nprint('Avg score {}'.format(np.mean(scores)))","metadata":{"execution":{"iopub.status.busy":"2024-05-22T02:36:36.524518Z","iopub.execute_input":"2024-05-22T02:36:36.525202Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}