{"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\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\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\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\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\nimport sklearn\nfrom sklearn.model_selection import train_test_split\n%matplotlib inline\nimport os\nimport torch\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df=pd.read_csv('/kaggle/input/cassava-leaf-disease-classification/train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install /kaggle/input/aefficientnet/efficientnet_pytorch-0.7.0-py3-none-any.whl\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from efficientnet_pytorch import EfficientNet\nmodel_transfer = EfficientNet.from_name('efficientnet-b3')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_transfer.load_state_dict(torch.load('../input/aefficientnet/efficientnet-b3-5fb5a3c3.pth'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train, df_valid=train_test_split(df,test_size=0.1,random_state=42,stratify=df['label'].values)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train=df_train.reset_index(drop=True)\ndf_valid=df_valid.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_valid.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train[:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_path = '../input/cassava-leaf-disease-classification/train_images/'\ntest_path = '../input/cassava-leaf-disease-classification/test_images/'\nsample = pd.read_csv('../input/cassava-leaf-disease-classification/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch\nfrom torch.utils.data import Dataset ,DataLoader\nimport pytorch_lightning as pl\nfrom torch import nn\nfrom torchvision import datasets\nimport torchvision.transforms as transforms","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class LeafDataset(Dataset):\n    \n    def __init__(self, dataframe, transform=None, test=False):\n        self.df = dataframe\n        self.transform = transform\n        self.test = test\n    \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, idx):\n        \n        label = self.df.label.values[idx]\n        p = self.df.image_id.values[idx]\n        \n        if self.test == False:\n            p_path = train_path + p\n        else:\n            p_path = test_path + p\n            \n        image = cv2.imread(p_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        image = transforms.ToPILImage()(image)\n        \n        if self.transform:\n            image = self.transform(image)\n        \n        return image,torch.tensor(label)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_transforms      = transforms.Compose([transforms.RandomHorizontalFlip(p=0.5),\n                                            transforms.RandomHorizontalFlip(p=0.5),\n                                            transforms.RandomResizedCrop(512),\n                                            transforms.ToTensor(),\n                                            transforms.Normalize([0.485, 0.456, 0.406],\n                                                                 [0.229, 0.224, 0.225])\n                                            ])\n\nvalid_transforms = transforms.Compose([transforms.Resize(550),\n                                       transforms.CenterCrop(512),\n                                       transforms.ToTensor(),\n                                       transforms.Normalize([0.485, 0.456, 0.406],\n                                                                 [0.229, 0.224, 0.225])]\n                                       )\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntest_transforms = transforms.Compose([transforms.Resize(550),\n                                       transforms.CenterCrop(512),\n                                       transforms.ToTensor(),\n                                       transforms.Normalize([0.485, 0.456, 0.406],\n                                                                 [0.229, 0.224, 0.225])]\n                                       )\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train[:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainset = LeafDataset(df_train, transform=train_transforms)\nvalidset = LeafDataset(df_valid, transform=valid_transforms)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testset = LeafDataset(sample, transform=test_transforms,test=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testset[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainset[0][1].dtype","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size   = 16\ntrainLoader  = torch.utils.data.DataLoader(trainset,\n                                           batch_size=batch_size,\n                                           shuffle=True,\n                                           num_workers=4)\n\nvalidLoader  = torch.utils.data.DataLoader(validset,\n                                           batch_size=16,\n                                           shuffle=False,\n                                           num_workers=4)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"testLoader  = torch.utils.data.DataLoader(testset,\n                                           batch_size=1,\n                                           shuffle=False,\n                                           num_workers=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loaders = {'train' : trainLoader, 'valid' : validLoader, 'test' : testLoader}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import torch.optim as optim","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for param in model_transfer.parameters():\n    param.requires_grad= False\nmodel_transfer._fc=nn.Linear(1536,5,bias=True)\nfc_parameters=model_transfer._fc.parameters()\nfor param in fc_parameters:\n    param.requires_grad= True\nsw_parameters=model_transfer._swish.parameters()\nfor param in sw_parameters:\n    param.requires_grad= True","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_transfer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"criterion= nn.CrossEntropyLoss()\noptimizer= optim.Adam(model_transfer._fc.parameters(),lr=5e-4)\nuse_cuda=torch.cuda.is_available()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_transfer=model_transfer.cuda()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from datetime import datetime\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import pytz\nIST = pytz.timezone('Asia/Kolkata')\nn_epochs = 20\nbest_acc = 0\nvalid_loss_min = np.Inf\nval_loss = []\nval_acc = []\ntrain_loss = []\ntrain_acc = []\ntotal_step = len(loaders['train'])\nfor epoch in range(1, n_epochs+1):\n    running_loss = 0.0\n    # scheduler.step(epoch)\n    correct = 0\n    total=0\n    datetime_ist = datetime.now(IST)\n    current_time = datetime_ist.strftime(\"%H:%M:%S\")\n    print(\"Current Time =\", current_time)\n    print(f'Epoch {epoch} :')\n    for batch_idx, (data,target) in enumerate(loaders['train']):\n        if use_cuda:\n            data, target = data.cuda(), target.cuda()\n        optimizer.zero_grad()\n        outputs = model_transfer(data)\n        loss = criterion(outputs, target)\n        loss.backward()\n        optimizer.step()\n        # print statistics\n        running_loss += loss.item()\n        _,pred = torch.max(outputs, dim=1)\n        correct += torch.sum(pred==target).item()\n        total += target.size(0)\n        train_acc.append(100 * correct / total)\n    train_loss.append(running_loss/total_step)\n    print(f'Training Loss: {np.mean(train_loss):.4f}, Training Accuracy: {(100 * correct / total):.4f}')\n    batch_loss = 0\n    total_t=0\n    correct_t=0\n    with torch.no_grad():\n        model_transfer.eval()\n        for batch_idx, (data_t, target_t) in enumerate(loaders['valid']):\n            if use_cuda:\n                data_t, target_t = data_t.cuda(), target_t.cuda()\n            outputs_t = model_transfer(data_t)\n            loss_t = criterion(outputs_t, target_t)\n            batch_loss += loss_t.item()\n            _,pred_t = torch.max(outputs_t, dim=1)\n            correct_t += torch.sum(pred_t==target_t).item()\n            total_t += target_t.size(0)\n        val_acc.append(100 * correct_t / total_t)\n        val_loss.append(batch_loss/len(loaders['valid']))\n        valacc=100 * correct_t / total_t\n        print(f'Validation Loss: {np.mean(val_loss):.4f}, Validation Accuracy: {(100 * correct_t / total_t):.4f}\\n')\n        # Saving the best weight \n        if valacc>best_acc:\n            best_acc = valacc\n            torch.save(model_transfer.state_dict(), 'model_transfer.pt')\n            print('Validation Accuracy Increased, saving current model..........\\n')\n    model_transfer.train()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1=model_transfer","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"model1.load_state_dict(torch.load('model_transfer.pt'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1.load_state_dict(torch.load('model_transfer.pt'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import cv2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_pred = []\n\nmodel1.eval()\nfor batch_idx, (datatest, targettest) in enumerate(loaders['test']):\n    if use_cuda:\n        datatest, targettest = datatest.cuda(), targettest.cuda()\n    pred= model1(datatest)\n    pred = pred.argmax(1).cpu().detach().numpy().astype('int')\n    test_pred.extend(pred)\n\nsample.label = test_pred\nsample.to_csv('submission.csv',index=False)\n   ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!cat submission.csv","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}