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

ML/Pytorch/pytorch_lightning/1. start code/simple_fc.py

@@ -0,0 +1,110 @@
+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
+from torch.utils.data import random_split
+
+
+class NN(nn.Module):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        self.fc1 = nn.Linear(input_size, 50)
+        self.fc2 = nn.Linear(50, num_classes)
+
+    def forward(self, x):
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x
+
+
+# Set device cuda for GPU if it's available otherwise run on the CPU
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+input_size = 784
+num_classes = 10
+learning_rate = 0.001
+batch_size = 64
+num_epochs = 3
+
+# Load Data
+entire_dataset = datasets.MNIST(
+    root="dataset/", train=True, transform=transforms.ToTensor(), download=True
+)
+train_ds, val_ds = random_split(entire_dataset, [50000, 10000])
+test_ds = datasets.MNIST(
+    root="dataset/", train=False, transform=transforms.ToTensor(), download=True
+)
+train_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+val_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+test_loader = DataLoader(dataset=test_ds, batch_size=batch_size, shuffle=False)
+
+# Initialize network
+model = NN(input_size=input_size, num_classes=num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train Network
+for epoch in range(num_epochs):
+    for batch_idx, (data, targets) in enumerate(tqdm(train_loader)):
+        # Get data to cuda if possible
+        data = data.to(device=device)
+        targets = targets.to(device=device)
+
+        # Get to correct shape
+        data = data.reshape(data.shape[0], -1)
+
+        # Forward
+        scores = model(data)
+        loss = criterion(scores, targets)
+
+        # Backward
+        optimizer.zero_grad()
+        loss.backward()
+
+        # Gradient descent or adam step
+        optimizer.step()
+
+
+# Check accuracy on training & test to see how good our model
+def check_accuracy(loader, model):
+    num_correct = 0
+    num_samples = 0
+    model.eval()
+
+    # We don't need to keep track of gradients here so we wrap it in torch.no_grad()
+    with torch.no_grad():
+        # Loop through the data
+        for x, y in loader:
+
+            # Move data to device
+            x = x.to(device=device)
+            y = y.to(device=device)
+
+            # Get to correct shape
+            x = x.reshape(x.shape[0], -1)
+
+            # Forward pass
+            scores = model(x)
+            _, predictions = scores.max(1)
+
+            # Check how many we got correct
+            num_correct += (predictions == y).sum()
+
+            # Keep track of number of samples
+            num_samples += predictions.size(0)
+
+    model.train()
+    return num_correct / num_samples
+
+
+# Check accuracy on training & test to see how good our model
+model.to(device)
+print(f"Accuracy on training set: {check_accuracy(train_loader, model)*100:.2f}")
+print(f"Accuracy on validation set: {check_accuracy(val_loader, model)*100:.2f}")
+print(f"Accuracy on test set: {check_accuracy(test_loader, model)*100:.2f}")

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)

ML/Pytorch/pytorch_lightning/2. LightningModule/simple_fc.py

@@ -0,0 +1,154 @@
+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
+from torch.utils.data import random_split
+import pytorch_lightning as pl 
+
+class NN(nn.Module):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        self.fc1 = nn.Linear(input_size, 50)
+        self.fc2 = nn.Linear(50, num_classes)
+
+    def forward(self, x):
+        x = F.relu(self.fc1(x))
+        x = self.fc2(x)
+        return x
+
+class NN(pl.LightningModule):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        self.fc1 = nn.Linear(input_size, 50)
+        self.fc2 = nn.Linear(50, num_classes)
+        self.loss_fn = nn.CrossEntropyLoss()
+
+    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)
+        self.log('train_loss', loss)
+        return loss
+    
+    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=0.001)
+
+# Set device cuda for GPU if it's available otherwise run on the CPU
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+
+input_size = 784
+num_classes = 10
+learning_rate = 0.001
+batch_size = 64
+num_epochs = 3
+
+# Load Data
+entire_dataset = datasets.MNIST(
+    root="dataset/", train=True, transform=transforms.ToTensor(), download=True
+)
+train_ds, val_ds = random_split(entire_dataset, [50000, 10000])
+test_ds = datasets.MNIST(
+    root="dataset/", train=False, transform=transforms.ToTensor(), download=True
+)
+train_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+val_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+test_loader = DataLoader(dataset=test_ds, batch_size=batch_size, shuffle=False)
+
+# Initialize network
+model = NN(input_size=input_size, num_classes=num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+# Train Network
+for epoch in range(num_epochs):
+    for batch_idx, (data, targets) in enumerate(tqdm(train_loader)):
+        # Get data to cuda if possible
+        data = data.to(device=device)
+        targets = targets.to(device=device)
+
+        # Get to correct shape
+        data = data.reshape(data.shape[0], -1)
+
+        # Forward
+        scores = model(data)
+        loss = criterion(scores, targets)
+
+        # Backward
+        optimizer.zero_grad()
+        loss.backward()
+
+        # Gradient descent or adam step
+        optimizer.step()
+
+
+# Check accuracy on training & test to see how good our model
+def check_accuracy(loader, model):
+    num_correct = 0
+    num_samples = 0
+    model.eval()
+
+    # We don't need to keep track of gradients here so we wrap it in torch.no_grad()
+    with torch.no_grad():
+        # Loop through the data
+        for x, y in loader:
+
+            # Move data to device
+            x = x.to(device=device)
+            y = y.to(device=device)
+
+            # Get to correct shape
+            x = x.reshape(x.shape[0], -1)
+
+            # Forward pass
+            scores = model(x)
+            _, predictions = scores.max(1)
+
+            # Check how many we got correct
+            num_correct += (predictions == y).sum()
+
+            # Keep track of number of samples
+            num_samples += predictions.size(0)
+
+    model.train()
+    return num_correct / num_samples
+
+
+# Check accuracy on training & test to see how good our model
+model.to(device)
+print(f"Accuracy on training set: {check_accuracy(train_loader, model)*100:.2f}")
+print(f"Accuracy on validation set: {check_accuracy(val_loader, model)*100:.2f}")
+print(f"Accuracy on test set: {check_accuracy(test_loader, model)*100:.2f}")

ML/Pytorch/pytorch_lightning/3. Lightning Trainer/simple_fc.py

@@ -0,0 +1,126 @@
+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
+from torch.utils.data import random_split
+import pytorch_lightning as pl 
+
+
+class NN(pl.LightningModule):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        self.fc1 = nn.Linear(input_size, 50)
+        self.fc2 = nn.Linear(50, num_classes)
+        self.loss_fn = nn.CrossEntropyLoss()
+
+    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)
+        self.log('train_loss', loss)
+        return loss
+    
+    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=0.001)
+
+# Set device cuda for GPU if it's available otherwise run on the CPU
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+input_size = 784
+num_classes = 10
+learning_rate = 0.001
+batch_size = 64
+num_epochs = 3
+
+# Load Data
+entire_dataset = datasets.MNIST(
+    root="dataset/", train=True, transform=transforms.ToTensor(), download=True
+)
+train_ds, val_ds = random_split(entire_dataset, [50000, 10000])
+test_ds = datasets.MNIST(
+    root="dataset/", train=False, transform=transforms.ToTensor(), download=True
+)
+train_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+val_loader = DataLoader(dataset=val_ds, batch_size=batch_size, shuffle=False)
+test_loader = DataLoader(dataset=test_ds, batch_size=batch_size, shuffle=False)
+
+# Initialize network
+model = NN(input_size=input_size, num_classes=num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+trainer = pl.Trainer(accelerator="gpu", devices=1, min_epochs=1, max_epochs=3, precision=16)
+trainer.fit(model, train_loader, val_loader)
+trainer.validate(model, val_loader)
+trainer.test(model, test_loader)
+
+# Check accuracy on training & test to see how good our model
+def check_accuracy(loader, model):
+    num_correct = 0
+    num_samples = 0
+    model.eval()
+
+    # We don't need to keep track of gradients here so we wrap it in torch.no_grad()
+    with torch.no_grad():
+        # Loop through the data
+        for x, y in loader:
+
+            # Move data to device
+            x = x.to(device=device)
+            y = y.to(device=device)
+
+            # Get to correct shape
+            x = x.reshape(x.shape[0], -1)
+
+            # Forward pass
+            scores = model(x)
+            _, predictions = scores.max(1)
+
+            # Check how many we got correct
+            num_correct += (predictions == y).sum()
+
+            # Keep track of number of samples
+            num_samples += predictions.size(0)
+
+    model.train()
+    return num_correct / num_samples
+
+
+# Check accuracy on training & test to see how good our model
+model.to(device)
+print(f"Accuracy on training set: {check_accuracy(train_loader, model)*100:.2f}")
+print(f"Accuracy on validation set: {check_accuracy(val_loader, model)*100:.2f}")
+print(f"Accuracy on test set: {check_accuracy(test_loader, model)*100:.2f}")

ML/Pytorch/pytorch_lightning/4. Metrics/simple_fc.py

@@ -0,0 +1,150 @@
+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
+from torch.utils.data import random_split
+import pytorch_lightning as pl 
+import torchmetrics 
+from torchmetrics import Metric
+
+
+class MyAccuracy(Metric):
+    def __init__(self):
+        super().__init__()
+        self.add_state("total", default=torch.tensor(0), dist_reduce_fx="sum")
+        self.add_state("correct", default=torch.tensor(0), dist_reduce_fx="sum")
+
+    def update(self, preds, target):
+        preds = torch.argmax(preds, dim=1)
+        assert preds.shape == target.shape
+        self.correct += torch.sum(preds == target)
+        self.total += target.numel()
+
+    def compute(self):
+        return self.correct.float() / self.total.float()
+
+
+class NN(pl.LightningModule):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        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.my_accuracy = MyAccuracy()
+        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.my_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=0.001)
+
+# Set device cuda for GPU if it's available otherwise run on the CPU
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+input_size = 784
+num_classes = 10
+learning_rate = 0.001
+batch_size = 64
+num_epochs = 3
+
+# Load Data
+entire_dataset = datasets.MNIST(
+    root="dataset/", train=True, transform=transforms.ToTensor(), download=True
+)
+train_ds, val_ds = random_split(entire_dataset, [50000, 10000])
+test_ds = datasets.MNIST(
+    root="dataset/", train=False, transform=transforms.ToTensor(), download=True
+)
+train_loader = DataLoader(dataset=train_ds, batch_size=batch_size, shuffle=True)
+val_loader = DataLoader(dataset=val_ds, batch_size=batch_size, shuffle=False)
+test_loader = DataLoader(dataset=test_ds, batch_size=batch_size, shuffle=False)
+
+# Initialize network
+model = NN(input_size=input_size, num_classes=num_classes).to(device)
+
+# Loss and optimizer
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.Adam(model.parameters(), lr=learning_rate)
+
+trainer = pl.Trainer(accelerator="gpu", devices=1, min_epochs=1, max_epochs=3, precision=16)
+trainer.fit(model, train_loader, val_loader)
+trainer.validate(model, val_loader)
+trainer.test(model, test_loader)
+
+# Check accuracy on training & test to see how good our model
+def check_accuracy(loader, model):
+    num_correct = 0
+    num_samples = 0
+    model.eval()
+
+    # We don't need to keep track of gradients here so we wrap it in torch.no_grad()
+    with torch.no_grad():
+        # Loop through the data
+        for x, y in loader:
+
+            # Move data to device
+            x = x.to(device=device)
+            y = y.to(device=device)
+
+            # Get to correct shape
+            x = x.reshape(x.shape[0], -1)
+
+            # Forward pass
+            scores = model(x)
+            _, predictions = scores.max(1)
+
+            # Check how many we got correct
+            num_correct += (predictions == y).sum()
+
+            # Keep track of number of samples
+            num_samples += predictions.size(0)
+
+    model.train()
+    return num_correct / num_samples
+
+
+# Check accuracy on training & test to see how good our model
+model.to(device)
+print(f"Accuracy on training set: {check_accuracy(train_loader, model)*100:.2f}")
+print(f"Accuracy on validation set: {check_accuracy(val_loader, model)*100:.2f}")
+print(f"Accuracy on test set: {check_accuracy(test_loader, model)*100:.2f}")

ML/Pytorch/pytorch_lightning/5. DataModule/simple_fc.py

@@ -0,0 +1,146 @@
+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
+from torch.utils.data import random_split
+import pytorch_lightning as pl 
+import torchmetrics 
+from torchmetrics import Metric
+
+
+class MyAccuracy(Metric):
+    def __init__(self):
+        super().__init__()
+        self.add_state("total", default=torch.tensor(0), dist_reduce_fx="sum")
+        self.add_state("correct", default=torch.tensor(0), dist_reduce_fx="sum")
+
+    def update(self, preds, target):
+        preds = torch.argmax(preds, dim=1)
+        assert preds.shape == target.shape
+        self.correct += torch.sum(preds == target)
+        self.total += target.numel()
+
+    def compute(self):
+        return self.correct.float() / self.total.float()
+
+
+class NN(pl.LightningModule):
+    def __init__(self, input_size, num_classes):
+        super().__init__()
+        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.my_accuracy = MyAccuracy()
+        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.my_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=0.001)
+
+
+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,
+        )
+
+# Set device cuda for GPU if it's available otherwise run on the CPU
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+# Hyperparameters
+input_size = 784
+num_classes = 10
+learning_rate = 0.001
+batch_size = 64
+num_epochs = 3
+
+model = NN(input_size=input_size, num_classes=num_classes)
+dm = MnistDataModule(data_dir="dataset/", batch_size=batch_size, num_workers=4)
+trainer = pl.Trainer(accelerator="gpu", devices=1, min_epochs=1, max_epochs=3, precision=16)
+trainer.fit(model, dm)
+trainer.validate(model, dm)
+trainer.test(model, dm)

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)

ML/Pytorch/pytorch_lightning/7. Callbacks/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/7. Callbacks/config.py

@@ -0,0 +1,15 @@
+# Training hyperparameters
+INPUT_SIZE = 784
+NUM_CLASSES = 10
+LEARNING_RATE = 0.001
+BATCH_SIZE = 64
+NUM_EPOCHS = 1000
+
+# Dataset
+DATA_DIR = "dataset/"
+NUM_WORKERS = 4
+
+# Compute related
+ACCELERATOR = "gpu"
+DEVICES = [0]
+PRECISION = 16

ML/Pytorch/pytorch_lightning/7. Callbacks/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/7. Callbacks/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/7. Callbacks/train.py

@@ -0,0 +1,31 @@
+import torch
+import pytorch_lightning as pl
+from model import NN
+from dataset import MnistDataModule
+import config
+from callbacks import MyPrintingCallback, EarlyStopping
+
+torch.set_float32_matmul_precision("medium") # to make lightning happy
+
+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=config.NUM_EPOCHS,
+        precision=config.PRECISION,
+        callbacks=[MyPrintingCallback(), EarlyStopping(monitor="val_loss")],
+    )
+    trainer.fit(model, dm)
+    trainer.validate(model, dm)
+    trainer.test(model, dm)

ML/Pytorch/pytorch_lightning/8. Logging Tensorboard/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/8. Logging Tensorboard/config.py

@@ -0,0 +1,15 @@
+# Training hyperparameters
+INPUT_SIZE = 784
+NUM_CLASSES = 10
+LEARNING_RATE = 0.001
+BATCH_SIZE = 64
+NUM_EPOCHS = 1000
+
+# Dataset
+DATA_DIR = "dataset/"
+NUM_WORKERS = 4
+
+# Compute related
+ACCELERATOR = "gpu"
+DEVICES = [0]
+PRECISION = 16

ML/Pytorch/pytorch_lightning/8. Logging Tensorboard/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/8. Logging Tensorboard/model.py

@@ -0,0 +1,79 @@
+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, 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):
+        x, y = batch
+        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,
+        )
+        
+        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 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/8. Logging Tensorboard/train.py

@@ -0,0 +1,34 @@
+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
+
+torch.set_float32_matmul_precision("medium") # to make lightning happy
+
+if __name__ == "__main__":
+    logger = TensorBoardLogger("tb_logs", name="mnist_model_v0")
+    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(
+        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)

ML/Pytorch/pytorch_lightning/9. Profiler/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/9. Profiler/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/9. Profiler/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/9. Profiler/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, 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):
+        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/9. Profiler/train.py

@@ -0,0 +1,40 @@
+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
+
+torch.set_float32_matmul_precision("medium") # to make lightning happy
+
+if __name__ == "__main__":
+    logger = TensorBoardLogger("tb_logs", name="mnist_model_v1")
+    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(
+        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)