{"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":"#

Import Required Libraries 📚

","metadata":{}},{"cell_type":"code","source":"import os\nimport gc\nimport cv2\nimport math\nimport copy\nimport time\nimport random\nimport glob\nfrom matplotlib import pyplot as plt\n\n# For data manipulation\nimport numpy as np\nimport pandas as pd\n\n# Pytorch Imports\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.nn.functional as F\nfrom torch.optim import lr_scheduler\nfrom torch.utils.data import Dataset, DataLoader\nfrom torch.cuda import amp\nimport torchvision\n\n# Utils\nimport joblib\nfrom tqdm import tqdm\nfrom collections import defaultdict\n\n# Sklearn Imports\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.model_selection import StratifiedKFold\n\n# For Image Models\nimport timm\n\n# Albumentations for augmentations\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\n\n# For colored terminal text\nfrom colorama import Fore, Back, Style\nb_ = Fore.BLUE\nsr_ = Style.RESET_ALL\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")\n\n# For descriptive error messages\nos.environ['CUDA_LAUNCH_BLOCKING'] = \"1\"","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:34.431111Z","iopub.execute_input":"2023-10-07T17:57:34.431528Z","iopub.status.idle":"2023-10-07T17:57:42.097633Z","shell.execute_reply.started":"2023-10-07T17:57:34.431507Z","shell.execute_reply":"2023-10-07T17:57:42.096718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Training Configuration ⚙️

","metadata":{}},{"cell_type":"code","source":"CONFIG = {\n \"seed\": 42,\n \"epochs\": 20,\n \"img_size\": 512,\n \"model_name\": \"tf_efficientnet_b0_ns\",\n \"checkpoint_path\" : \"/kaggle/input/tf-efficientnet/pytorch/tf-efficientnet-b0/1/tf_efficientnet_b0_aa-827b6e33.pth\",\n \"num_classes\": 8,\n \"train_batch_size\": 32,\n \"valid_batch_size\": 64,\n \"learning_rate\": 1e-4,\n \"scheduler\": 'CosineAnnealingLR',\n \"min_lr\": 1e-6,\n \"T_max\": 500,\n \"weight_decay\": 1e-6,\n \"fold\" : 0,\n \"n_fold\": 5,\n \"n_accumulate\": 1,\n \"device\": torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\"),\n}","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.099347Z","iopub.execute_input":"2023-10-07T17:57:42.099789Z","iopub.status.idle":"2023-10-07T17:57:42.130706Z","shell.execute_reply.started":"2023-10-07T17:57:42.099756Z","shell.execute_reply":"2023-10-07T17:57:42.129816Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Set Seed for Reproducibility

","metadata":{}},{"cell_type":"code","source":"def set_seed(seed=42):\n '''Sets the seed of the entire notebook so results are the same every time we run.\n This is for REPRODUCIBILITY.'''\n np.random.seed(seed)\n torch.manual_seed(seed)\n torch.cuda.manual_seed(seed)\n # When running on the CuDNN backend, two further options must be set\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n # Set a fixed value for the hash seed\n os.environ['PYTHONHASHSEED'] = str(seed)\n \nset_seed(CONFIG['seed'])","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.132399Z","iopub.execute_input":"2023-10-07T17:57:42.133247Z","iopub.status.idle":"2023-10-07T17:57:42.153011Z","shell.execute_reply.started":"2023-10-07T17:57:42.133208Z","shell.execute_reply":"2023-10-07T17:57:42.152204Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT_DIR = '/kaggle/input/UBC-OCEAN'\nTRAIN_DIR = '/kaggle/input/UBC-OCEAN/train_thumbnails'\nTEST_DIR = '/kaggle/input/UBC-OCEAN/test_images'","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.155658Z","iopub.execute_input":"2023-10-07T17:57:42.156116Z","iopub.status.idle":"2023-10-07T17:57:42.164389Z","shell.execute_reply.started":"2023-10-07T17:57:42.156095Z","shell.execute_reply":"2023-10-07T17:57:42.163483Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_train_file_path(image_id):\n return f\"{TRAIN_DIR}/{image_id}_thumbnail.png\"\n# return f\"{TRAIN_DIR}/{image_id}.png\"","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.165636Z","iopub.execute_input":"2023-10-07T17:57:42.16594Z","iopub.status.idle":"2023-10-07T17:57:42.174399Z","shell.execute_reply.started":"2023-10-07T17:57:42.165911Z","shell.execute_reply":"2023-10-07T17:57:42.173477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Read the Data 📖

","metadata":{}},{"cell_type":"code","source":"train_images = sorted(glob.glob(f\"{TRAIN_DIR}/*.png\"))","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.175584Z","iopub.execute_input":"2023-10-07T17:57:42.176257Z","iopub.status.idle":"2023-10-07T17:57:42.248637Z","shell.execute_reply.started":"2023-10-07T17:57:42.176229Z","shell.execute_reply":"2023-10-07T17:57:42.247619Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv(f\"{ROOT_DIR}/train.csv\")\ndf['file_path'] = df['image_id'].apply(get_train_file_path)\ndf = df[ df[\"file_path\"].isin(train_images) ].reset_index(drop=True)\ndf","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.24996Z","iopub.execute_input":"2023-10-07T17:57:42.250403Z","iopub.status.idle":"2023-10-07T17:57:42.299576Z","shell.execute_reply.started":"2023-10-07T17:57:42.25037Z","shell.execute_reply":"2023-10-07T17:57:42.298842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"encoder = LabelEncoder()\ndf['label'] = encoder.fit_transform(df['label'])\n\nwith open(\"label_encoder.pkl\", \"wb\") as fp:\n joblib.dump(encoder, fp)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.303001Z","iopub.execute_input":"2023-10-07T17:57:42.303773Z","iopub.status.idle":"2023-10-07T17:57:42.312667Z","shell.execute_reply.started":"2023-10-07T17:57:42.303742Z","shell.execute_reply":"2023-10-07T17:57:42.311692Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"CONFIG['T_max'] = df.shape[0] * (CONFIG[\"n_fold\"]-1) * CONFIG['epochs'] // CONFIG['train_batch_size'] // CONFIG[\"n_fold\"]\nCONFIG['T_max']","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.315304Z","iopub.execute_input":"2023-10-07T17:57:42.316383Z","iopub.status.idle":"2023-10-07T17:57:42.323239Z","shell.execute_reply.started":"2023-10-07T17:57:42.31635Z","shell.execute_reply":"2023-10-07T17:57:42.321919Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Create Folds

","metadata":{}},{"cell_type":"code","source":"skf = StratifiedKFold(n_splits=CONFIG['n_fold'])\n\nfor fold, ( _, val_) in enumerate(skf.split(X=df, y=df.label)):\n df.loc[val_ , \"kfold\"] = int(fold)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.328132Z","iopub.execute_input":"2023-10-07T17:57:42.32879Z","iopub.status.idle":"2023-10-07T17:57:42.34279Z","shell.execute_reply.started":"2023-10-07T17:57:42.328756Z","shell.execute_reply":"2023-10-07T17:57:42.342111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Dataset Class

","metadata":{}},{"cell_type":"code","source":"class UBCDataset(Dataset):\n def __init__(self, df, transforms=None):\n self.df = df\n self.file_names = df['file_path'].values\n self.labels = df['label'].values\n self.transforms = transforms\n \n def __len__(self):\n return len(self.df)\n \n def __getitem__(self, index):\n img_path = self.file_names[index]\n img = cv2.imread(img_path)\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n label = self.labels[index]\n \n if self.transforms:\n img = self.transforms(image=img)[\"image\"]\n \n return {\n 'image': img,\n 'label': torch.tensor(label, dtype=torch.long)\n }","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.344275Z","iopub.execute_input":"2023-10-07T17:57:42.344899Z","iopub.status.idle":"2023-10-07T17:57:42.353536Z","shell.execute_reply.started":"2023-10-07T17:57:42.34487Z","shell.execute_reply":"2023-10-07T17:57:42.352549Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Augmentations

","metadata":{}},{"cell_type":"code","source":"data_transforms = {\n \"train\": A.Compose([\n A.Resize(CONFIG['img_size'], CONFIG['img_size']),\n A.ShiftScaleRotate(shift_limit=0.1, \n scale_limit=0.15, \n rotate_limit=60, \n p=0.5),\n A.HueSaturationValue(\n hue_shift_limit=0.2, \n sat_shift_limit=0.2, \n val_shift_limit=0.2, \n p=0.5\n ),\n A.RandomBrightnessContrast(\n brightness_limit=(-0.1,0.1), \n contrast_limit=(-0.1, 0.1), \n p=0.5\n ),\n A.Normalize(\n mean=[0.485, 0.456, 0.406], \n std=[0.229, 0.224, 0.225], \n max_pixel_value=255.0, \n p=1.0\n ),\n ToTensorV2()], p=1.),\n \n \"valid\": A.Compose([\n A.Resize(CONFIG['img_size'], CONFIG['img_size']),\n A.Normalize(\n mean=[0.485, 0.456, 0.406], \n std=[0.229, 0.224, 0.225], \n max_pixel_value=255.0, \n p=1.0\n ),\n ToTensorV2()], p=1.)\n}","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.355231Z","iopub.execute_input":"2023-10-07T17:57:42.355861Z","iopub.status.idle":"2023-10-07T17:57:42.368267Z","shell.execute_reply.started":"2023-10-07T17:57:42.355828Z","shell.execute_reply":"2023-10-07T17:57:42.367325Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

GeM Pooling

\n\nCode taken from GeM Pooling Explained\n\n![](https://i.imgur.com/thTgYWG.jpg)","metadata":{}},{"cell_type":"code","source":"class GeM(nn.Module):\n def __init__(self, p=3, eps=1e-6):\n super(GeM, self).__init__()\n self.p = nn.Parameter(torch.ones(1)*p)\n self.eps = eps\n\n def forward(self, x):\n return self.gem(x, p=self.p, eps=self.eps)\n \n def gem(self, x, p=3, eps=1e-6):\n return F.avg_pool2d(x.clamp(min=eps).pow(p), (x.size(-2), x.size(-1))).pow(1./p)\n \n def __repr__(self):\n return self.__class__.__name__ + \\\n '(' + 'p=' + '{:.4f}'.format(self.p.data.tolist()[0]) + \\\n ', ' + 'eps=' + str(self.eps) + ')'","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.373575Z","iopub.execute_input":"2023-10-07T17:57:42.374378Z","iopub.status.idle":"2023-10-07T17:57:42.382788Z","shell.execute_reply.started":"2023-10-07T17:57:42.374342Z","shell.execute_reply":"2023-10-07T17:57:42.381827Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Create Model

","metadata":{}},{"cell_type":"code","source":"class UBCModel(nn.Module):\n def __init__(self, model_name, num_classes, pretrained=True, checkpoint_path=None):\n super(UBCModel, self).__init__()\n self.model = timm.create_model(model_name, pretrained=pretrained, checkpoint_path=checkpoint_path)\n\n in_features = self.model.classifier.in_features\n self.model.classifier = nn.Identity()\n self.model.global_pool = nn.Identity()\n self.pooling = GeM()\n self.linear = nn.Linear(in_features, num_classes)\n self.softmax = nn.Softmax(dim=1)\n\n def forward(self, images):\n features = self.model(images)\n pooled_features = self.pooling(features).flatten(1)\n output = self.linear(pooled_features)\n return output\n\n \nmodel = UBCModel(CONFIG['model_name'], CONFIG['num_classes'], checkpoint_path=CONFIG['checkpoint_path'])\nmodel.to(CONFIG['device']);","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:42.384044Z","iopub.execute_input":"2023-10-07T17:57:42.384913Z","iopub.status.idle":"2023-10-07T17:57:46.298818Z","shell.execute_reply.started":"2023-10-07T17:57:42.384885Z","shell.execute_reply":"2023-10-07T17:57:46.297854Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Loss Function

","metadata":{}},{"cell_type":"code","source":"def criterion(outputs, labels):\n return nn.CrossEntropyLoss()(outputs, labels)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.300102Z","iopub.execute_input":"2023-10-07T17:57:46.300438Z","iopub.status.idle":"2023-10-07T17:57:46.305236Z","shell.execute_reply.started":"2023-10-07T17:57:46.300402Z","shell.execute_reply":"2023-10-07T17:57:46.304185Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Training Function

","metadata":{}},{"cell_type":"code","source":"def train_one_epoch(model, optimizer, scheduler, dataloader, device, epoch):\n model.train()\n \n dataset_size = 0\n running_loss = 0.0\n running_acc = 0.0\n \n bar = tqdm(enumerate(dataloader), total=len(dataloader))\n for step, data in bar:\n images = data['image'].to(device, dtype=torch.float)\n labels = data['label'].to(device, dtype=torch.long)\n \n batch_size = images.size(0)\n \n outputs = model(images)\n loss = criterion(outputs, labels)\n loss = loss / CONFIG['n_accumulate']\n \n loss.backward()\n \n if (step + 1) % CONFIG['n_accumulate'] == 0:\n optimizer.step()\n\n # zero the parameter gradients\n optimizer.zero_grad()\n\n if scheduler is not None:\n scheduler.step()\n \n _, predicted = torch.max(model.softmax(outputs), 1)\n acc = torch.sum( predicted == labels )\n \n running_loss += (loss.item() * batch_size)\n running_acc += acc.item()\n dataset_size += batch_size\n \n epoch_loss = running_loss / dataset_size\n epoch_acc = running_acc / dataset_size\n \n bar.set_postfix(Epoch=epoch, Train_Loss=epoch_loss, Train_Acc=epoch_acc,\n LR=optimizer.param_groups[0]['lr'])\n gc.collect()\n \n return epoch_loss, epoch_acc","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.306601Z","iopub.execute_input":"2023-10-07T17:57:46.307515Z","iopub.status.idle":"2023-10-07T17:57:46.318523Z","shell.execute_reply.started":"2023-10-07T17:57:46.307479Z","shell.execute_reply":"2023-10-07T17:57:46.31765Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Validation Function

","metadata":{}},{"cell_type":"code","source":"@torch.inference_mode()\ndef valid_one_epoch(model, dataloader, device, epoch):\n model.eval()\n \n dataset_size = 0\n running_loss = 0.0\n running_acc = 0.0\n \n bar = tqdm(enumerate(dataloader), total=len(dataloader))\n for step, data in bar: \n images = data['image'].to(device, dtype=torch.float)\n labels = data['label'].to(device, dtype=torch.long)\n \n batch_size = images.size(0)\n\n outputs = model(images)\n loss = criterion(outputs, labels)\n\n _, predicted = torch.max(model.softmax(outputs), 1)\n acc = torch.sum( predicted == labels )\n\n running_loss += (loss.item() * batch_size)\n running_acc += acc.item()\n dataset_size += batch_size\n \n epoch_loss = running_loss / dataset_size\n epoch_acc = running_acc / dataset_size\n \n bar.set_postfix(Epoch=epoch, Valid_Loss=epoch_loss, Valid_Acc=epoch_acc,\n LR=optimizer.param_groups[0]['lr']) \n \n gc.collect()\n \n return epoch_loss, epoch_acc","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.319747Z","iopub.execute_input":"2023-10-07T17:57:46.320336Z","iopub.status.idle":"2023-10-07T17:57:46.332633Z","shell.execute_reply.started":"2023-10-07T17:57:46.320309Z","shell.execute_reply":"2023-10-07T17:57:46.331688Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Run Training

","metadata":{}},{"cell_type":"code","source":"def run_training(model, optimizer, scheduler, device, num_epochs):\n if torch.cuda.is_available():\n print(\"[INFO] Using GPU: {}\\n\".format(torch.cuda.get_device_name()))\n \n start = time.time()\n best_model_wts = copy.deepcopy(model.state_dict())\n best_epoch_acc = -np.inf\n history = defaultdict(list)\n \n for epoch in range(1, num_epochs + 1): \n gc.collect()\n train_epoch_loss, train_epoch_acc = train_one_epoch(model, optimizer, scheduler, \n dataloader=train_loader, \n device=CONFIG['device'], epoch=epoch)\n \n val_epoch_loss, val_epoch_acc = valid_one_epoch(model, valid_loader, device=CONFIG['device'], \n epoch=epoch)\n \n history['Train Loss'].append(train_epoch_loss)\n history['Valid Loss'].append(val_epoch_loss)\n history['Train Accuracy'].append(train_epoch_acc)\n history['Valid Accuracy'].append(val_epoch_acc)\n history['lr'].append( scheduler.get_lr()[0] )\n \n # deep copy the model\n if best_epoch_acc <= val_epoch_acc:\n print(f\"{b_}Validation Accuracy Improved ({best_epoch_acc} ---> {val_epoch_acc})\")\n best_epoch_acc = val_epoch_acc\n best_model_wts = copy.deepcopy(model.state_dict())\n PATH = \"Acc{:.2f}_Loss{:.4f}_epoch{:.0f}.bin\".format(best_epoch_acc, val_epoch_loss, epoch)\n torch.save(model.state_dict(), PATH)\n # Save a model file from the current directory\n print(f\"Model Saved{sr_}\")\n \n print()\n \n end = time.time()\n time_elapsed = end - start\n print('Training complete in {:.0f}h {:.0f}m {:.0f}s'.format(\n time_elapsed // 3600, (time_elapsed % 3600) // 60, (time_elapsed % 3600) % 60))\n print(\"Best Accuracy: {:.4f}\".format(best_epoch_acc))\n \n # load best model weights\n model.load_state_dict(best_model_wts)\n \n return model, history","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.333873Z","iopub.execute_input":"2023-10-07T17:57:46.334448Z","iopub.status.idle":"2023-10-07T17:57:46.346874Z","shell.execute_reply.started":"2023-10-07T17:57:46.334421Z","shell.execute_reply":"2023-10-07T17:57:46.346021Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def fetch_scheduler(optimizer):\n if CONFIG['scheduler'] == 'CosineAnnealingLR':\n scheduler = lr_scheduler.CosineAnnealingLR(optimizer,T_max=CONFIG['T_max'], \n eta_min=CONFIG['min_lr'])\n elif CONFIG['scheduler'] == 'CosineAnnealingWarmRestarts':\n scheduler = lr_scheduler.CosineAnnealingWarmRestarts(optimizer,T_0=CONFIG['T_0'], \n eta_min=CONFIG['min_lr'])\n elif CONFIG['scheduler'] == None:\n return None\n \n return scheduler","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.348246Z","iopub.execute_input":"2023-10-07T17:57:46.349027Z","iopub.status.idle":"2023-10-07T17:57:46.361939Z","shell.execute_reply.started":"2023-10-07T17:57:46.348998Z","shell.execute_reply":"2023-10-07T17:57:46.361095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def prepare_loaders(df, fold):\n df_train = df[df.kfold != fold].reset_index(drop=True)\n df_valid = df[df.kfold == fold].reset_index(drop=True)\n \n train_dataset = UBCDataset(df_train, transforms=data_transforms[\"train\"])\n valid_dataset = UBCDataset(df_valid, transforms=data_transforms[\"valid\"])\n\n train_loader = DataLoader(train_dataset, batch_size=CONFIG['train_batch_size'], \n num_workers=2, shuffle=True, pin_memory=True, drop_last=True)\n valid_loader = DataLoader(valid_dataset, batch_size=CONFIG['valid_batch_size'], \n num_workers=2, shuffle=False, pin_memory=True)\n \n return train_loader, valid_loader","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.363131Z","iopub.execute_input":"2023-10-07T17:57:46.363612Z","iopub.status.idle":"2023-10-07T17:57:46.378328Z","shell.execute_reply.started":"2023-10-07T17:57:46.363584Z","shell.execute_reply":"2023-10-07T17:57:46.37741Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Prepare Dataloaders","metadata":{}},{"cell_type":"code","source":"train_loader, valid_loader = prepare_loaders(df, fold=CONFIG[\"fold\"])","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.379595Z","iopub.execute_input":"2023-10-07T17:57:46.380174Z","iopub.status.idle":"2023-10-07T17:57:46.390891Z","shell.execute_reply.started":"2023-10-07T17:57:46.380134Z","shell.execute_reply":"2023-10-07T17:57:46.390066Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Define Optimizer and Scheduler","metadata":{}},{"cell_type":"code","source":"optimizer = optim.Adam(model.parameters(), lr=CONFIG['learning_rate'], \n weight_decay=CONFIG['weight_decay'])\nscheduler = fetch_scheduler(optimizer)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.392406Z","iopub.execute_input":"2023-10-07T17:57:46.392948Z","iopub.status.idle":"2023-10-07T17:57:46.401482Z","shell.execute_reply.started":"2023-10-07T17:57:46.39292Z","shell.execute_reply":"2023-10-07T17:57:46.400573Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Start Training","metadata":{}},{"cell_type":"code","source":"model, history = run_training(model, optimizer, scheduler,\n device=CONFIG['device'],\n num_epochs=CONFIG['epochs'])","metadata":{"execution":{"iopub.status.busy":"2023-10-07T17:57:46.402783Z","iopub.execute_input":"2023-10-07T17:57:46.403382Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = pd.DataFrame.from_dict(history)\nhistory.to_csv(\"history.csv\", index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Logs

","metadata":{}},{"cell_type":"code","source":"plt.plot( range(history.shape[0]), history[\"Train Loss\"].values, label=\"Train Loss\")\nplt.plot( range(history.shape[0]), history[\"Valid Loss\"].values, label=\"Valid Loss\")\nplt.xlabel(\"epochs\")\nplt.ylabel(\"Loss\")\nplt.grid()\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.plot( range(history.shape[0]), history[\"Train Accuracy\"].values, label=\"Train Accuracy\")\nplt.plot( range(history.shape[0]), history[\"Valid Accuracy\"].values, label=\"Valid Accuracy\")\nplt.xlabel(\"epochs\")\nplt.ylabel(\"Accuracy\")\nplt.grid()\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.plot( range(history.shape[0]), history[\"lr\"].values, label=\"lr\")\nplt.xlabel(\"epochs\")\nplt.ylabel(\"lr\")\nplt.grid()\nplt.legend()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}