{"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":"2023-10-07T18:51:43.438396Z","iopub.execute_input":"2023-10-07T18:51:43.438754Z","iopub.status.idle":"2023-10-07T18:51:43.446112Z","shell.execute_reply.started":"2023-10-07T18:51:43.438727Z","shell.execute_reply":"2023-10-07T18:51:43.445126Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Training Configuration ⚙️

","metadata":{}},{"cell_type":"code","source":"CONFIG = {\n \"seed\": 42,\n \"img_size\": 512,\n \"model_name\": \"tf_efficientnet_b0_ns\",\n \"num_classes\": 8,\n \"valid_batch_size\": 64,\n \"device\": torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\"),\n}","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:43.766655Z","iopub.execute_input":"2023-10-07T18:51:43.76725Z","iopub.status.idle":"2023-10-07T18:51:43.772149Z","shell.execute_reply.started":"2023-10-07T18:51:43.767219Z","shell.execute_reply":"2023-10-07T18:51:43.770969Z"},"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":"2023-10-07T18:51:44.012901Z","iopub.execute_input":"2023-10-07T18:51:44.013816Z","iopub.status.idle":"2023-10-07T18:51:44.019595Z","shell.execute_reply.started":"2023-10-07T18:51:44.013782Z","shell.execute_reply":"2023-10-07T18:51:44.018615Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"ROOT_DIR = '/kaggle/input/UBC-OCEAN'\nTEST_DIR = '/kaggle/input/UBC-OCEAN/test_thumbnails'\n\nLABEL_ENCODER_BIN = \"/kaggle/input/ubc-pytorch-cnn-training-fold1of5/label_encoder.pkl\"\nBEST_WEIGHT = \"/kaggle/input/ubc-pytorch-cnn-training-fold1of5/Acc0.69_Loss0.9592_epoch20.bin\"","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:44.159767Z","iopub.execute_input":"2023-10-07T18:51:44.160055Z","iopub.status.idle":"2023-10-07T18:51:44.164511Z","shell.execute_reply.started":"2023-10-07T18:51:44.160031Z","shell.execute_reply":"2023-10-07T18:51:44.163277Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_test_file_path(image_id):\n return f\"{TEST_DIR}/{image_id}_thumbnail.png\"","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:44.288624Z","iopub.execute_input":"2023-10-07T18:51:44.289324Z","iopub.status.idle":"2023-10-07T18:51:44.29408Z","shell.execute_reply.started":"2023-10-07T18:51:44.289269Z","shell.execute_reply":"2023-10-07T18:51:44.29311Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Read the Data 📖

","metadata":{}},{"cell_type":"code","source":"df = pd.read_csv(f\"{ROOT_DIR}/test.csv\")\ndf['file_path'] = df['image_id'].apply(get_test_file_path)\ndf['label'] = 0 # dummy\ndf","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:44.569431Z","iopub.execute_input":"2023-10-07T18:51:44.569774Z","iopub.status.idle":"2023-10-07T18:51:44.585139Z","shell.execute_reply.started":"2023-10-07T18:51:44.569742Z","shell.execute_reply":"2023-10-07T18:51:44.584189Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_sub = pd.read_csv(f\"{ROOT_DIR}/sample_submission.csv\")\ndf_sub","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:44.70123Z","iopub.execute_input":"2023-10-07T18:51:44.701766Z","iopub.status.idle":"2023-10-07T18:51:44.725126Z","shell.execute_reply.started":"2023-10-07T18:51:44.70173Z","shell.execute_reply":"2023-10-07T18:51:44.72375Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"encoder = joblib.load( LABEL_ENCODER_BIN )","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:44.838583Z","iopub.execute_input":"2023-10-07T18:51:44.838859Z","iopub.status.idle":"2023-10-07T18:51:44.844228Z","shell.execute_reply.started":"2023-10-07T18:51:44.838836Z","shell.execute_reply":"2023-10-07T18:51:44.843248Z"},"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":"2023-10-07T18:51:45.226073Z","iopub.execute_input":"2023-10-07T18:51:45.226616Z","iopub.status.idle":"2023-10-07T18:51:45.233398Z","shell.execute_reply.started":"2023-10-07T18:51:45.226582Z","shell.execute_reply":"2023-10-07T18:51:45.232507Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"#

Augmentations

","metadata":{}},{"cell_type":"code","source":"data_transforms = {\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":"2023-10-07T18:51:45.507484Z","iopub.execute_input":"2023-10-07T18:51:45.507756Z","iopub.status.idle":"2023-10-07T18:51:45.512958Z","shell.execute_reply.started":"2023-10-07T18:51:45.507734Z","shell.execute_reply":"2023-10-07T18:51:45.511907Z"},"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":"2023-10-07T18:51:45.810848Z","iopub.execute_input":"2023-10-07T18:51:45.811695Z","iopub.status.idle":"2023-10-07T18:51:45.81964Z","shell.execute_reply.started":"2023-10-07T18:51:45.811668Z","shell.execute_reply":"2023-10-07T18:51:45.818438Z"},"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=False, checkpoint_path=None):\n super(UBCModel, self).__init__()\n self.model = timm.create_model(model_name, pretrained=pretrained)\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'])\nmodel.load_state_dict(torch.load( BEST_WEIGHT ))\nmodel.to(CONFIG['device']);","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:46.11481Z","iopub.execute_input":"2023-10-07T18:51:46.115083Z","iopub.status.idle":"2023-10-07T18:51:46.301446Z","shell.execute_reply.started":"2023-10-07T18:51:46.115059Z","shell.execute_reply":"2023-10-07T18:51:46.300512Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Prepare Dataloaders","metadata":{}},{"cell_type":"code","source":"test_dataset = UBCDataset(df, transforms=data_transforms[\"valid\"])\ntest_loader = DataLoader(test_dataset, batch_size=CONFIG['valid_batch_size'], \n num_workers=2, shuffle=False, pin_memory=True)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:46.401749Z","iopub.execute_input":"2023-10-07T18:51:46.402622Z","iopub.status.idle":"2023-10-07T18:51:46.407968Z","shell.execute_reply.started":"2023-10-07T18:51:46.402586Z","shell.execute_reply":"2023-10-07T18:51:46.407055Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Start Inference","metadata":{}},{"cell_type":"code","source":"preds = []\nwith torch.no_grad():\n bar = tqdm(enumerate(test_loader), total=len(test_loader))\n for step, data in bar: \n images = data['image'].to(CONFIG[\"device\"], dtype=torch.float) \n batch_size = images.size(0)\n outputs = model(images)\n _, predicted = torch.max(model.softmax(outputs), 1)\n preds.append( predicted.detach().cpu().numpy() )\npreds = np.concatenate(preds).flatten()\npred_labels = encoder.inverse_transform( preds )","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:51:46.675927Z","iopub.execute_input":"2023-10-07T18:51:46.676268Z","iopub.status.idle":"2023-10-07T18:52:00.62748Z","shell.execute_reply.started":"2023-10-07T18:51:46.676239Z","shell.execute_reply":"2023-10-07T18:52:00.626389Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_sub[\"label\"] = pred_labels\ndf_sub.to_csv(\"submission.csv\", index=False)","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:52:00.629781Z","iopub.execute_input":"2023-10-07T18:52:00.630352Z","iopub.status.idle":"2023-10-07T18:52:00.638717Z","shell.execute_reply.started":"2023-10-07T18:52:00.630319Z","shell.execute_reply":"2023-10-07T18:52:00.637755Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df_sub","metadata":{"execution":{"iopub.status.busy":"2023-10-07T18:52:00.640159Z","iopub.execute_input":"2023-10-07T18:52:00.640766Z","iopub.status.idle":"2023-10-07T18:52:00.659678Z","shell.execute_reply.started":"2023-10-07T18:52:00.640735Z","shell.execute_reply":"2023-10-07T18:52:00.658782Z"},"trusted":true},"execution_count":null,"outputs":[]}]}