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

ML/Pytorch/pytorch_lightning/10. Multi-GPU/callbacks.py

@@ -0,0 +1,12 @@
+from pytorch_lightning.callbacks import EarlyStopping, Callback
+
+class MyPrintingCallback(Callback):
+    def __init__(self):
+        super().__init__()
+
+    def on_train_start(self, trainer, pl_module):
+        print("Starting to train!")
+
+    def on_train_end(self, trainer, pl_module):
+        print("Training is done.")
+

ML/Pytorch/pytorch_lightning/10. Multi-GPU/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, 1]
+PRECISION = 16

ML/Pytorch/pytorch_lightning/10. Multi-GPU/dataset.py

@@ -0,0 +1,64 @@
+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
+from torchvision.transforms import RandomHorizontalFlip, RandomVerticalFlip
+
+
+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.Compose([
+                transforms.RandomVerticalFlip(),
+                transforms.RandomHorizontalFlip(),
+                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/10. Multi-GPU/model.py

@@ -0,0 +1,89 @@
+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
+import torchvision
+
+
+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, 1_000_000)
+        self.fc2 = nn.Linear(1_000_000, 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):
+        x, y = batch
+        loss, scores, y = self._common_step(batch, batch_idx)
+
+        self.log_dict(
+            {
+                "train_loss": loss,
+            },
+            on_step=False,
+            on_epoch=True,
+            prog_bar=True,
+        )
+        
+        if batch_idx % 100 == 0:
+            x = x[:8]
+            grid = torchvision.utils.make_grid(x.view(-1, 1, 28, 28))
+            self.logger.experiment.add_image("mnist_images", grid, self.global_step)
+
+        return {"loss": loss, "scores": scores, "y": y}
+    
+    def training_epoch_end(self, outputs):
+        scores = torch.cat([x["scores"] for x in outputs])
+        y = torch.cat([x["y"] for x in outputs])
+        self.log_dict(
+            {
+                "train_acc": self.accuracy(scores, y),
+                "train_f1": self.f1_score(scores, y),
+            },
+            on_step=False,
+            on_epoch=True,
+            prog_bar=True,
+        )
+
+    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/10. Multi-GPU/train.py

@@ -0,0 +1,43 @@
+import torch
+import pytorch_lightning as pl
+from model import NN
+from dataset import MnistDataModule
+import config
+from callbacks import MyPrintingCallback, EarlyStopping
+from pytorch_lightning.loggers import TensorBoardLogger
+from pytorch_lightning.profilers import PyTorchProfiler
+from pytorch_lightning.strategies import DeepSpeedStrategy
+
+torch.set_float32_matmul_precision("medium") # to make lightning happy
+
+if __name__ == "__main__":
+    logger = TensorBoardLogger("tb_logs", name="mnist_model_v1")
+    strategy = DeepSpeedStrategy()
+    profiler = PyTorchProfiler(
+        on_trace_ready=torch.profiler.tensorboard_trace_handler("tb_logs/profiler0"),
+        schedule=torch.profiler.schedule(skip_first=10, wait=1, warmup=1, active=20),
+    )
+    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(
+        strategy=strategy,
+        profiler=profiler,
+        logger=logger,
+        accelerator=config.ACCELERATOR,
+        devices=config.DEVICES,
+        min_epochs=1,
+        max_epochs=config.NUM_EPOCHS,
+        precision=config.PRECISION,
+        callbacks=[MyPrintingCallback(), EarlyStopping(monitor="val_loss")],
+    )
+    trainer.fit(model, dm)
+    trainer.validate(model, dm)
+    trainer.test(model, dm)