{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import torch\nimport torchvision\nfrom torchvision.models import resnet18\nimport torch.nn as nn\nimport torchvision.transforms as transforms\nimport torch.optim as optim\nfrom torch.utils.data import DataLoader,Dataset\nfrom torch.utils.data.sampler import SubsetRandomSampler\nfrom PIL import Image\nfrom sklearn.preprocessing import LabelEncoder\nfrom tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"le = LabelEncoder()\ndf = pd.read_csv('../input/dog-breed-identification/labels.csv')\ndf.head()\ndf['breed'] = le.fit_transform(df['breed'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class DogDataset(Dataset):\n    def __init__(self,csv,transform):\n        self.data = csv\n        self.transform = transform\n        self.labels = torch.eye(120)[self.data['breed']]\n        \n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self,idx):\n        image_path = os.path.join('../input/dog-breed-identification/train/'+self.data.loc[idx]['id']+'.jpg')\n        image = Image.open(image_path)\n        image = self.transform(image)\n        label = torch.tensor(self.data.loc[idx]['breed'])\n        return {'images':image,'labels':label}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"simple_transform = transforms.Compose([transforms.Resize((224,224)),transforms.ToTensor(),transforms.Normalize([0.496,0.456,0.406],[0.229,0.224,0.225])])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = DogDataset(df,simple_transform)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_size = len(train_dataset)\nindicies = list(range(data_size))\nsplit = int(np.round(0.2*data_size,0))\ntraining_indicies = indicies[split:]\nvalidation_indices = indicies[:split]\ntrain_sampler = SubsetRandomSampler(training_indicies)\nvalid_sampler = SubsetRandomSampler(validation_indices)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_loader = DataLoader(train_dataset,batch_size=32,sampler=train_sampler)\nvalid_loader = DataLoader(train_dataset,batch_size=32,sampler=valid_sampler)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = resnet18(pretrained=False)\nmodel.load_state_dict(torch.load('../input/resnet18/resnet18.pth'))\nfor param in model.parameters():\n    param.require_grad = False\nmodel.fc = nn.Linear(512,120)\nfc_parameters = model.fc.parameters()\nfor param in fc_parameters:\n    param.require_grad = True\nmodel = model.cuda()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"criteria= nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(),lr = 0.001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def fit(epochs,model,optimizer,criteria):\n    for epoch in range(epochs):\n        training_loss = 0.0\n        validation_loss = 0.0\n        correct = 0\n        total = 0\n        print('{}/{} Epochs'.format(epoch+1,epochs))\n        model.train()\n        for batch_idx,d in enumerate(train_loader):\n            data = d['images'].cuda()\n            target = d['labels'].cuda()\n            \n            optimizer.zero_grad()\n            output = model(data)\n            loss = criteria(output,target)\n            \n            loss.backward()\n            optimizer.step()\n            \n            training_loss = training_loss + (1/(batch_idx+1)*(loss.data-training_loss))\n            if batch_idx%20==0:\n                print('Training Loss is {}'.format(training_loss))\n                \n            pred = output.data.max(1,keepdim = True)[1]\n            correct +=np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())\n            total +=data.size(0)\n            print('Batch ID {} is having training Accuracy of {}'.format(batch_idx,100*correct/total))\n            \n        model.eval()\n        for batch_idx,d in enumerate(valid_loader):\n            data = d['images'].cuda()\n            target = d['labels'].cuda()\n            \n            output = model(data)\n            loss = criteria(output,target)\n            validation_loss = validation_loss + ((1)/(batch_idx+1)*(loss.data-validation_loss))\n            \n            if batch_idx % 20==0:\n                print('Validation Loss is {}'.format(validation_loss))\n            pred = output.data.max(1,keepdim=True)[1]\n            correct+= np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())\n            total += data.size(0)\n            print('Batch id {} is having Validation Accuracy of {}'.format(batch_idx,100*correct/total))\n            \n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fit(10,model,optimizer,criteria)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv('../input/dog-breed-identification/sample_submission.csv')\nsample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class Prediction(Dataset):\n    def __init__(self,csv,transform):\n        self.data = pd.read_csv(csv)\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.data)\n    \n    def __getitem__(self,idx):\n        image_path = os.path.join('../input/dog-breed-identification/test/'+self.data.loc[idx]['id']+'.jpg')\n        image = Image.open(image_path)\n        image = self.transform(image)\n        return {'images':image}","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dataset = Prediction('../input/dog-breed-identification/sample_submission.csv',simple_transform)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_loader = DataLoader(test_dataset)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = []\nfor batch_idx, d in enumerate(test_loader):\n    data = d['images'].cuda()\n    output = model(data)\n    output = output.cpu().detach().numpy()\n    predict.append(list(output[0]))\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in tqdm(range(len(predict))):\n    sample.iloc[i,1:]  = predict[i]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample.to_csv('sample_submission.csv',index = False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}