add lightning code, finetuning whisper, recommender system neural collaborative filtering

ML/Pytorch/pytorch_lightning/6. Restructuring/config.py

@@ -0,0 +1,15 @@
+# Training hyperparameters
+INPUT_SIZE = 784
+NUM_CLASSES = 10
+LEARNING_RATE = 0.001
+BATCH_SIZE = 64
+NUM_EPOCHS = 3
+
+# Dataset
+DATA_DIR = "dataset/"
+NUM_WORKERS = 4
+
+# Compute related
+ACCELERATOR = "gpu"
+DEVICES = [0]
+PRECISION = 16

ML/Pytorch/pytorch_lightning/6. Restructuring/dataset.py

@@ -0,0 +1,59 @@
+import torch
+import torch.nn.functional as F
+import torchvision.datasets as datasets
+import torchvision.transforms as transforms
+from torch import nn, optim
+from torch.utils.data import DataLoader
+from torch.utils.data import random_split
+import pytorch_lightning as pl
+
+
+class MnistDataModule(pl.LightningDataModule):
+    def __init__(self, data_dir, batch_size, num_workers):
+        super().__init__()
+        self.data_dir = data_dir
+        self.batch_size = batch_size
+        self.num_workers = num_workers
+
+    def prepare_data(self):
+        datasets.MNIST(self.data_dir, train=True, download=True)
+        datasets.MNIST(self.data_dir, train=False, download=True)
+
+    def setup(self, stage):
+        entire_dataset = datasets.MNIST(
+            root=self.data_dir,
+            train=True,
+            transform=transforms.ToTensor(),
+            download=False,
+        )
+        self.train_ds, self.val_ds = random_split(entire_dataset, [50000, 10000])
+        self.test_ds = datasets.MNIST(
+            root=self.data_dir,
+            train=False,
+            transform=transforms.ToTensor(),
+            download=False,
+        )
+
+    def train_dataloader(self):
+        return DataLoader(
+            self.train_ds,
+            batch_size=self.batch_size,
+            num_workers=self.num_workers,
+            shuffle=True,
+        )
+
+    def val_dataloader(self):
+        return DataLoader(
+            self.val_ds,
+            batch_size=self.batch_size,
+            num_workers=self.num_workers,
+            shuffle=False,
+        )
+
+    def test_dataloader(self):
+        return DataLoader(
+            self.test_ds,
+            batch_size=self.batch_size,
+            num_workers=self.num_workers,
+            shuffle=False,
+        )

ML/Pytorch/pytorch_lightning/6. Restructuring/model.py

@@ -0,0 +1,71 @@
+import torch
+import torch.nn.functional as F
+import torchvision.datasets as datasets
+import torchvision.transforms as transforms
+from torch import nn, optim
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+import pytorch_lightning as pl
+import torchmetrics
+from torchmetrics import Metric
+
+
+class NN(pl.LightningModule):
+    def __init__(self, input_size, learning_rate, num_classes):
+        super().__init__()
+        self.lr = learning_rate
+        self.fc1 = nn.Linear(input_size, 50)
+        self.fc2 = nn.Linear(50, num_classes)
+        self.loss_fn = nn.CrossEntropyLoss()
+        self.accuracy = torchmetrics.Accuracy(
+            task="multiclass", num_classes=num_classes
+        )
+        self.f1_score = torchmetrics.F1Score(task="multiclass", num_classes=num_classes)
+
+    def forward(self, x):
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x
+
+    def training_step(self, batch, batch_idx):
+        loss, scores, y = self._common_step(batch, batch_idx)
+        accuracy = self.accuracy(scores, y)
+        f1_score = self.f1_score(scores, y)
+        self.log_dict(
+            {
+                "train_loss": loss,
+                "train_accuracy": accuracy,
+                "train_f1_score": f1_score,
+            },
+            on_step=False,
+            on_epoch=True,
+            prog_bar=True,
+        )
+        return {"loss": loss, "scores": scores, "y": y}
+
+    def validation_step(self, batch, batch_idx):
+        loss, scores, y = self._common_step(batch, batch_idx)
+        self.log("val_loss", loss)
+        return loss
+
+    def test_step(self, batch, batch_idx):
+        loss, scores, y = self._common_step(batch, batch_idx)
+        self.log("test_loss", loss)
+        return loss
+
+    def _common_step(self, batch, batch_idx):
+        x, y = batch
+        x = x.reshape(x.size(0), -1)
+        scores = self.forward(x)
+        loss = self.loss_fn(scores, y)
+        return loss, scores, y
+
+    def predict_step(self, batch, batch_idx):
+        x, y = batch
+        x = x.reshape(x.size(0), -1)
+        scores = self.forward(x)
+        preds = torch.argmax(scores, dim=1)
+        return preds
+
+    def configure_optimizers(self):
+        return optim.Adam(self.parameters(), lr=self.lr)

ML/Pytorch/pytorch_lightning/6. Restructuring/train.py

@@ -0,0 +1,27 @@
+import torch
+import pytorch_lightning as pl
+from model import NN
+from dataset import MnistDataModule
+import config
+
+if __name__ == "__main__":
+    model = NN(
+        input_size=config.INPUT_SIZE,
+        learning_rate=config.LEARNING_RATE,
+        num_classes=config.NUM_CLASSES,
+    )
+    dm = MnistDataModule(
+        data_dir=config.DATA_DIR,
+        batch_size=config.BATCH_SIZE,
+        num_workers=config.NUM_WORKERS,
+    )
+    trainer = pl.Trainer(
+        accelerator=config.ACCELERATOR,
+        devices=config.DEVICES,
+        min_epochs=1,
+        max_epochs=3,
+        precision=config.PRECISION,
+    )
+    trainer.fit(model, dm)
+    trainer.validate(model, dm)
+    trainer.test(model, dm)