{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Directory settings\n# ====================================================\nimport os\n\nOUTPUT_DIR = './'\nMODEL_DIR = '../input/resnet-merged-fold012/'\nif not os.path.exists(OUTPUT_DIR):\n    os.makedirs(OUTPUT_DIR)\n    \nTRAIN_PATH = '../input/cassava-leaf-disease-classification/train_images'\nTEST_PATH = '../input/cassava-leaf-disease-classification/test_images'\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# CFG"},{"metadata":{"trusted":true},"cell_type":"code","source":"#### ====================================================\n# CFG\n# ====================================================\nclass CFG:\n    debug=False\n    num_workers=8\n    model_name='resnext50_32x4d'\n    size=512\n    batch_size=32\n    seed=2020\n    target_size=5\n    target_col='label'\n    n_fold=5\n    trn_fold= [0,1,2] #[0, 1, 2, 3, 4]\n    pth_dir = [MODEL_DIR + x for x in os.listdir(MODEL_DIR)]\n    inference=True","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Library"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Library\n# ====================================================\nimport sys\nsys.path.append('../input/pytorch-image-models/pytorch-image-models-master')\n\nimport os\nimport math\nimport time\nimport random\nimport shutil\nfrom pathlib import Path\nfrom contextlib import contextmanager\nfrom collections import defaultdict, Counter\n\nimport scipy as sp\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn import preprocessing\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import StratifiedKFold\n\nfrom tqdm.auto import tqdm\nfrom functools import partial\n\nimport cv2\nfrom PIL import Image\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.optim import Adam, SGD\nimport torchvision.models as models\nfrom torch.nn.parameter import Parameter\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.optim.lr_scheduler import CosineAnnealingWarmRestarts, CosineAnnealingLR, ReduceLROnPlateau\n\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\n\nimport timm\n\nimport warnings \nwarnings.filterwarnings('ignore')\n\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Utils"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Utils\n# ====================================================\ndef get_score(y_true, y_pred):\n    return accuracy_score(y_true, y_pred)\n\n\n@contextmanager\ndef timer(name):\n    t0 = time.time()\n    LOGGER.info(f'[{name}] start')\n    yield\n    LOGGER.info(f'[{name}] done in {time.time() - t0:.0f} s.')\n\n\ndef init_logger(log_file=OUTPUT_DIR+'inference.log'):\n    from logging import getLogger, INFO, FileHandler,  Formatter,  StreamHandler\n    logger = getLogger(__name__)\n    logger.setLevel(INFO)\n    handler1 = StreamHandler()\n    handler1.setFormatter(Formatter(\"%(message)s\"))\n    handler2 = FileHandler(filename=log_file)\n    handler2.setFormatter(Formatter(\"%(message)s\"))\n    logger.addHandler(handler1)\n    logger.addHandler(handler2)\n    return logger\n\n#LOGGER = init_logger()\n\ndef seed_torch(seed=42):\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\nseed_torch(seed=CFG.seed)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Loading"},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Dataset\n# ====================================================\nclass TestDataset(Dataset):\n    def __init__(self, df, transform=None):\n        self.df = df\n        self.file_names = df['image_id'].values\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        file_name = self.file_names[idx]\n        file_path = f'{TEST_PATH}/{file_name}'\n        image = cv2.imread(file_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        if self.transform:\n            augmented = self.transform(image=image)\n            image = augmented['image']\n        return image","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Transforms"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Transforms\n# ====================================================\ndef get_transforms(*, data):\n    if data == 'valid':\n        return A.Compose([\n            A.CenterCrop(CFG.size, CFG.size),\n            A.Resize(CFG.size, CFG.size),\n            A.Normalize(\n                mean=[0.485, 0.456, 0.406],\n                std=[0.229, 0.224, 0.225],\n            ),\n            ToTensorV2(),\n        ])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# MODEL"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# MODEL\n# ====================================================\n# class CustomResNext(nn.Module):\n#     def __init__(self, model_name='resnext50_32x4d', pretrained=False):\n#         super().__init__()\n#         self.model = timm.create_model(model_name, pretrained=pretrained)\n#         n_features = self.model.fc.in_features\n#         self.model.fc = nn.Linear(n_features, CFG.target_size)\n\n#     def forward(self, x):\n#         x = self.model(x)\n#         return x\nclass CustomResNext(nn.Module):\n    def __init__(self, model_name='resnext50_32x4d', pretrained=False):\n        super().__init__()\n        #self.model = timm.create_model(model_name, pretrained=pretrained)\n        backbone = timm.create_model(model_name, pretrained=pretrained)\n        self.backbone = nn.Sequential(*backbone.children())[:-2]\n        n_features = backbone.fc.in_features\n        self.classifier = nn.Linear(n_features, 5)\n        self.pool = nn.AdaptiveAvgPool2d((1, 1))\n        #self.model.fc = nn.Linear(n_features, CFG.target_size)\n\n    def forward_features(self, x):\n        x = self.backbone(x)\n        return x\n\n    def forward(self, x):\n        feats = self.forward_features(x)\n        x = self.pool(feats).view(x.size(0), -1)\n        x = self.classifier(x)\n        return x, feats","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Helper functions"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Helper functions\n# ====================================================\ndef load_state(model_path):\n    model = CustomResNext(CFG.model_name, pretrained=False)\n    try:  # single GPU model_file\n        model.load_state_dict(torch.load(model_path)['model'], strict=True)\n        state_dict = torch.load(model_path)['model']\n    except:  # multi GPU model_file\n        state_dict = torch.load(model_path)['model']\n        state_dict = {k[7:] if k.startswith('module.') else k: state_dict[k] for k in state_dict.keys()}\n\n    return state_dict\n\n\ndef inference(model, states, test_loader, device):\n    model.to(device)\n    tk0 = tqdm(enumerate(test_loader), total=len(test_loader))\n    probs = []\n    for i, (images) in tk0:\n        images = images.to(device)\n        avg_preds = []\n        for state in states:\n            model.load_state_dict(state)\n            model.eval()\n            with torch.no_grad():\n                y_preds, _ = model(images)\n                # print(y_preds.softmax(1))\n            avg_preds.append(y_preds.softmax(1).to('cpu').numpy())\n        avg_preds = np.mean(avg_preds, axis=0)\n        probs.append(avg_preds)\n    probs = np.concatenate(probs)\n    return probs","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# inference\n# ====================================================\nmodel = CustomResNext(CFG.model_name, pretrained=False)\n\n#states = [load_state(MODEL_DIR+ f'{CFG.model_name}_fold{fold}_best.pth') for fold in CFG.trn_fold]\nstates = [load_state(x) for x in CFG.pth_dir]\n\ntest_dataset = TestDataset(test, transform=get_transforms(data='valid'))\ntest_loader = DataLoader(test_dataset, batch_size=CFG.batch_size, shuffle=False, \n                         num_workers=CFG.num_workers, pin_memory=True)\npredictions = inference(model, states, test_loader, device)\n# submission\ntest['label'] = predictions.argmax(1)\ntest[['image_id', 'label']].to_csv('submission.csv', index=False)\ntest.head()\nprint(test)","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}