{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train_csv=pd.read_csv(\"/kaggle/input/cassava-leaf-disease-classification/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_csv.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\ntrain_csv\ntrain_csv['split'] = np.random.randn(train_csv.shape[0], 1)\n\nmsk = np.random.rand(len(train_csv)) <= 0.7\n\ntrain = train_csv[msk]\nval = train_csv[~msk]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(columns=[\"split\",],inplace=True)\nval.drop(columns=[\"split\",],inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.reset_index(inplace=True)\ntrain.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val.reset_index(inplace=True)\nval.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.label.unique()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub=pd.read_csv(\"/kaggle/input/cassava-leaf-disease-classification/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from __future__ import print_function, division\n\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nfrom torch.optim import lr_scheduler\nimport numpy as np\nimport torchvision\nfrom torchvision import datasets, models, transforms\nimport matplotlib.pyplot as plt\nimport time\nimport os\nimport copy\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from PIL import Image\nimport os\nimport torch\nfrom skimage import io, transform\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom torch.utils.data import Dataset, DataLoader\nfrom torchvision import transforms, utils\nclass CustomDataset(Dataset):\n    def __init__(self, csv_file, id_col, target_col, root_dir, transform=None):\n        \"\"\"\n        Args:\n            csv_file   (string):             Path to the csv file with annotations.\n            root_dir   (string):             Directory with all the images.\n            id_col     (string):             csv id column name.\n            target_col (string):             csv target column name.\n            sufix      (string, optional):   Optional sufix for samples.\n            transform  (callable, optional): Optional transform to be applied on a sample.\n        \"\"\"\n        self.data      = csv_file\n        self.id        = id_col\n        self.target    = target_col\n        self.root      = root_dir\n        self.transform = transform\n\n    def __len__(self):\n        return len(self.data)\n\n    def __getitem__(self, idx):\n        img_name = self.data.loc[idx, self.id]\n        image = Image.open(os.path.join(self.root, img_name))\n        if self.transform is not None:\n            image = self.transform(image)\n        label = self.data.loc[idx, self.target]\n        return image, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Data augmentation and normalization for training\n# Just normalization for validation\ndata_transforms = {\n    'train': transforms.Compose([\n        transforms.RandomResizedCrop(224),\n        transforms.RandomHorizontalFlip(),\n        transforms.ToTensor(),\n        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n    ]),\n    'val': transforms.Compose([\n        transforms.Resize(256),\n        transforms.CenterCrop(224),\n        transforms.ToTensor(),\n        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])\n    ]),\n}\n\nparams = {\n    'id_col':     'image_id',  \n    'target_col': 'label' ,\n    'transform':  data_transforms['train']\n}\ntrain_dir=\"../input/cassava-leaf-disease-classification/train_images\"\n#train_csv=\"../input/cassava-leaf-disease-classification/train.csv\"\ntrain_dataset = CustomDataset(csv_file=train, root_dir=train_dir, **params)\nval_dataset=CustomDataset(csv_file=val, root_dir=train_dir, **params)\n\ntrain_loader = DataLoader(train_dataset, batch_size=32, shuffle=True, num_workers=0)\nval_loader=DataLoader(val_dataset, batch_size=32, shuffle=True, num_workers=0)\ndataloaders={\"train\":train_loader,\"val\":val_loader}\ndataset_sizes = {\"train\": len(train_dataset) ,\"val\":len(val_dataset)}\ndevice = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def imshow(inp, title=None):\n    \"\"\"Imshow for Tensor.\"\"\"\n    inp = inp.numpy().transpose((1, 2, 0))\n    mean = np.array([0.485, 0.456, 0.406])\n    std = np.array([0.229, 0.224, 0.225])\n    inp = std * inp + mean\n    inp = np.clip(inp, 0, 1)\n    plt.imshow(inp)\n    if title is not None:\n        plt.title(title)\n    plt.pause(0.001)  # pause a bit so that plots are updated\n\n\n# Get a batch of training data\ninputs, classes = next(iter(dataloaders['train']))\n# Make a grid from batch\nout = torchvision.utils.make_grid(inputs)\n\nimshow(out, title=[classes])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_model(model, criterion, optimizer, scheduler, num_epochs=25):\n    since = time.time()\n\n    best_model_wts = copy.deepcopy(model.state_dict())\n    best_acc = 0.0\n\n    for epoch in range(num_epochs):\n        print('Epoch {}/{}'.format(epoch, num_epochs - 1))\n        print('-' * 10)\n\n        # Each epoch has a training and validation phase\n        for phase in ['train', 'val']:\n            if phase == 'train':\n                model.train()  # Set model to training mode\n                dataloader=train_loader\n            else:\n                model.eval()   # Set model to evaluate mode\n                dataloader=val_loader\n\n            running_loss = 0.0\n            running_corrects = 0\n\n            # Iterate over data.\n            for inputs, labels in dataloader:\n                inputs = inputs.to(device)\n                labels=torch.tensor(labels)\n                labels = labels.to(device)\n\n                # zero the parameter gradients\n                optimizer.zero_grad()\n\n                # forward\n                # track history if only in train\n                with torch.set_grad_enabled(phase == 'train'):\n                    outputs = model(inputs)\n                    _, preds = torch.max(outputs, 1)\n                    loss = criterion(outputs, labels)\n\n                    # backward + optimize only if in training phase\n                    if phase == 'train':\n                        loss.backward()\n                        optimizer.step()\n\n                # statistics\n                running_loss += loss.item() * inputs.size(0)\n                running_corrects += torch.sum(preds == labels.data)\n            if phase == 'train':\n                scheduler.step()\n\n            epoch_loss = running_loss / dataset_sizes[phase]\n            epoch_acc = running_corrects.double() / dataset_sizes[phase]\n\n            print('{} Loss: {:.4f} Acc: {:.4f}'.format(\n                phase, epoch_loss, epoch_acc))\n\n            # deep copy the model\n            if phase == 'val' and epoch_acc > best_acc:\n                best_acc = epoch_acc\n                best_model_wts = copy.deepcopy(model.state_dict())\n\n        print()\n\n    time_elapsed = time.time() - since\n    print('Training complete in {:.0f}m {:.0f}s'.format(\n        time_elapsed // 60, time_elapsed % 60))\n    print('Best val Acc: {:4f}'.format(best_acc))\n\n    # load best model weights\n    model.load_state_dict(best_model_wts)\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def visualize_model(model, num_images=6):\n    was_training = model.training\n    model.eval()\n    images_so_far = 0\n    fig = plt.figure()\n\n    with torch.no_grad():\n        for i, (inputs, labels) in enumerate(dataloaders['val']):\n            inputs = inputs.to(device)\n            labels = labels.to(device)\n\n            outputs = model(inputs)\n            _, preds = torch.max(outputs, 1)\n\n            for j in range(inputs.size()[0]):\n                images_so_far += 1\n                ax = plt.subplot(num_images//2, 2, images_so_far)\n                ax.axis('off')\n                ax.set_title('predicted: {}'.format(preds[j]))\n                imshow(inputs.cpu().data[j])\n\n                if images_so_far == num_images:\n                    model.train(mode=was_training)\n                    return\n        model.train(mode=was_training)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2 \n  \n# Save image in set directory \n# Read RGB image \nimg = cv2.imread('../input/cassava-leaf-disease-classification/test_images/2216849948.jpg') \nimg.size","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cache_dir = \"/root/.cache/torch/checkpoints/\"\nif not os.path.exists(cache_dir):\n    os.makedirs(cache_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!cp ../input/pretrained-pytorch-models/* $cache_dir","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls $cache_dir","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_ft = models.resnet18(pretrained=True)\nnum_ftrs = model_ft.fc.in_features\n# Here the size of each output sample is set to 2.\n# Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).\nmodel_ft.fc = nn.Linear(num_ftrs, 5)\n\nmodel_ft = model_ft.to(device)\n\ncriterion = nn.CrossEntropyLoss()\n\n# Observe that all parameters are being optimized\noptimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)\n\n# Decay LR by a factor of 0.1 every 7 epochs\nexp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler,\n                       num_epochs=25)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"visualize_model(model_ft)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test=pd.read_csv(\"/kaggle/input/cassava-leaf-disease-classification/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dir=\"../input/cassava-leaf-disease-classification/test_images\"\n#train_csv=\"../input/cassava-leaf-disease-classification/train.csv\"\ntest_dataset = CustomDataset(csv_file=test, root_dir=test_dir, **params)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_loader=DataLoader(test_dataset, batch_size=1, shuffle=True, num_workers=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def visualize_model_for_test(model, num_images=1):\n    was_training = model.training\n    model.eval()\n    images_so_far = 0\n    fig = plt.figure()\n\n    with torch.no_grad():\n        for i, (inputs, labels) in enumerate(test_loader):\n            inputs = inputs.to(device)\n            labels = labels.to(device)\n\n            outputs = model(inputs)\n            _, preds = torch.max(outputs, 1)\n\n            for j in range(inputs.size()[0]):\n                images_so_far += 1\n                ax = plt.subplot()\n                ax.axis('off')\n                ax.set_title('predicted: {}'.format(preds[j]))\n                imshow(inputs.cpu().data[j])\n\n                if images_so_far == num_images:\n                    model.train(mode=was_training)\n                    return preds\n        model.train(mode=was_training)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds=visualize_model_for_test(model_ft)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y=torch.Tensor.cpu(preds).detach().numpy()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit = pd.DataFrame({'image_id': test['image_id'].values, 'label': y})\nsubmit.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}