{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np \nimport pandas as pd\nfrom PIL import Image\nimport os\n\nimport torch\nimport torch.nn as nn\nimport torchvision\nimport torchvision.transforms as transforms\nfrom torch.utils.data import Dataset, DataLoader","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"BATCH = 16\nEPOCHS = 5\n\nLR = 0.0001\nIM_SIZE = 128\n\nDEVICE = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n\npath = '../input/plant-pathology-2021-fgvc8/'\nTRAIN_DIR = path + 'train_images/'\nTEST_DIR = path + 'test_images/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(path + 'train.csv')\ntrain_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['labels'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NUM_CL = len(train_df['labels'].value_counts())\nNUM_CL\n# 12","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.read_csv(path + 'sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn import preprocessing\n\nle = preprocessing.LabelEncoder()\nle.fit(train_df['labels'])\ntrain_df['label_id'] = le.transform(train_df['labels'])\ntrain_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# for Inference\n\nclass_map = dict(sorted(train_df[['label_id', 'labels']].values.tolist()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# !!! Just for speed up training\ntr_df = train_df[:3000]\nprint(len(tr_df))\nX_Train, Y_Train = tr_df['image'].values, tr_df['label_id'].values\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Transform = transforms.Compose(\n    [transforms.ToTensor(),\n    transforms.Resize((IM_SIZE, IM_SIZE)),\n    transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class GetData(Dataset):\n    def __init__(self, Dir, FNames, Labels, Transform):\n        self.dir = Dir\n        self.fnames = FNames\n        self.transform = Transform\n        self.labels = Labels         \n        \n    def __len__(self):\n        return len(self.fnames)\n\n    def __getitem__(self, index):       \n        x = Image.open(os.path.join(self.dir, self.fnames[index]))\n    \n        if \"train\" in self.dir:             \n            return self.transform(x), self.labels[index]\n        elif \"test\" in self.dir:            \n            return self.transform(x), self.fnames[index]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainset = GetData(TRAIN_DIR, X_Train, Y_Train, Transform)\ntrainloader = DataLoader(trainset, batch_size=BATCH, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"next(iter(trainloader))[0].shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = torchvision.models.resnet34()\nmodel.fc = nn.Linear(512, NUM_CL, bias=True)\nmodel = model.to(DEVICE)\n\ncriterion = nn.CrossEntropyLoss()\noptimizer = torch.optim.Adam(model.parameters(), lr=LR)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\nfor epoch in range(EPOCHS):\n    tr_loss = 0.0\n\n    model = model.train()\n\n    for i, (images, labels) in enumerate(trainloader):        \n        images = images.to(DEVICE)\n        labels = labels.to(DEVICE)       \n        logits = model(images.float())       \n        loss = criterion(logits, labels)\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n\n        tr_loss += loss.detach().item()\n    \n    model.eval()\n    print('Epoch: %d | Loss: %.4f'%(epoch, tr_loss / i))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_Test = [name for name in (os.listdir(TEST_DIR))]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testset = GetData(TEST_DIR, X_Test, None, Transform)\ntestloader = DataLoader(testset, batch_size=1, shuffle=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\ns_ls = []\n\nwith torch.no_grad():\n    model.eval()\n    for image, fname in testloader: \n        image = image.to(DEVICE)\n        \n        logits = model(image)        \n        ps = torch.exp(logits)        \n        _, top_class = ps.topk(1, dim=1)\n        \n        for pred in top_class:\n            s_ls.append([fname[0], pred.item()])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df = pd.DataFrame.from_records(s_ls, columns=['image', 'label_id'])\npred_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred_df['labels'] = pred_df['label_id'].map(class_map)\npred_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pred_df[['image', 'labels']]\nsub.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub.to_csv(\"submission.csv\", index=False)","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}