{"cells":[{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"!curl https://raw.githubusercontent.com/pytorch/xla/master/contrib/scripts/env-setup.py -o pytorch-xla-env-setup.py\n!python pytorch-xla-env-setup.py --version nightly --apt-packages libomp5 libopenblas-dev","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install pytorch_lightning -q","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"_kg_hide-output":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)\nimport glob\nimport matplotlib.pyplot as plt\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\n%matplotlib inline\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\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":{"trusted":true},"cell_type":"code","source":"df = pd.read_csv('/kaggle/input/cassava-leaf-disease-classification/train.csv')\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nfrom torch import nn\nfrom torch.nn import functional as F\nfrom PIL import Image\nfrom torch.utils.data import DataLoader\nfrom torch.utils.data import random_split\nfrom torchvision import transforms,models\nimport pytorch_lightning as pl\nimport albumentations as A\n\nclass ImageClassifier(pl.LightningModule):\n    def __init__(self):\n        super().__init__()\n        self.model = models.resnet34(pretrained=True)\n        self.fc = nn.Linear(1000,5)\n        \n    def forward(self, x):\n        embedding = self.model(x)\n        out = self.fc(embedding)\n        return out\n    \n    def configure_optimizers(self):\n        optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)\n        return optimizer\n    \n    def training_step(self, train_batch, batch_idx):\n        x, y = train_batch\n        z = self.model(x)    \n        y_hat = self.fc(z)\n        loss = F.cross_entropy(y_hat, y)\n        self.log('train_loss', loss)\n        return loss\n\n    def validation_step(self, val_batch, batch_idx):\n        x, y = val_batch\n        z = self.model(x)    \n        y_hat = self.fc(z)\n        loss = F.cross_entropy(y_hat, y)\n        self.log('val_loss', loss)\n        return \n        \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class LeafDataset():\n    def __init__(self,df,aug):\n        self.df = df\n        self.aug = aug\n    \n    def __len__(self):\n        return len(self.df)\n    \n    def __getitem__(self, idx):\n        img = Image.open('/kaggle/input/cassava-leaf-disease-classification/train_images/' + df.image_id.values[idx])\n        img = img.resize((224,224),resample=Image.BILINEAR)\n        img = np.array(img)\n        label = df.label.values[idx] \n        aug_img = self.aug(image=img)['image']\n        aug_img = np.transpose(aug_img,(2,0,1)).astype(np.float32)\n        return torch.tensor(aug_img,dtype=torch.float),torch.tensor(label,dtype=torch.long)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# data\ntfm = A.Compose(\n        [\n            A.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225),max_pixel_value=255.0,always_apply=True),\n        ])\ndataset = LeafDataset(df,tfm)\ntrain_ds, val_ds = random_split(dataset, [15000, 6397])\ntrain_loader = DataLoader(train_ds, batch_size=8,num_workers=4)\nval_loader = DataLoader(val_ds, batch_size=8,num_workers=4)\n# model\nmodel = ImageClassifier()\n# training\ntrainer = pl.Trainer(max_epochs=3,tpu_cores=8)\n#trainer = pl.Trainer(gpus=4, num_nodes=8, precision=16, limit_train_batches=0.5)\ntrainer.fit(model, train_loader, val_loader)","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}