pip install lightning

pip install lightning['extra']

conda install lightning -c conda-forge

pip install https://github.com/Lightning-AI/lightning/archive/refs/heads/release/stable.zip -U

pip install https://github.com/Lightning-AI/lightning/archive/refs/heads/master.zip -U

pip install -iU https://test.pypi.org/simple/ pytorch-lightning

# main.py
# ! pip install torchvision
import torch, torch.nn as nn, torch.utils.data as data, torchvision as tv, torch.nn.functional as F
import lightning as L

# --------------------------------
# Step 1: Define a LightningModule
# --------------------------------
# A LightningModule (nn.Module subclass) defines a full *system*
# (ie: an LLM, diffusion model, autoencoder, or simple image classifier).


class LitAutoEncoder(L.LightningModule):
    def __init__(self):
        super().__init__()
        self.encoder = nn.Sequential(nn.Linear(28 * 28, 128), nn.ReLU(), nn.Linear(128, 3))
        self.decoder = nn.Sequential(nn.Linear(3, 128), nn.ReLU(), nn.Linear(128, 28 * 28))

    def forward(self, x):
        # in lightning, forward defines the prediction/inference actions
        embedding = self.encoder(x)
        return embedding

    def training_step(self, batch, batch_idx):
        # training_step defines the train loop. It is independent of forward
        x, _ = batch
        x = x.view(x.size(0), -1)
        z = self.encoder(x)
        x_hat = self.decoder(z)
        loss = F.mse_loss(x_hat, x)
        self.log("train_loss", loss)
        return loss

    def configure_optimizers(self):
        optimizer = torch.optim.Adam(self.parameters(), lr=1e-3)
        return optimizer


# -------------------
# Step 2: Define data
# -------------------
dataset = tv.datasets.MNIST(".", download=True, transform=tv.transforms.ToTensor())
train, val = data.random_split(dataset, [55000, 5000])

# -------------------
# Step 3: Train
# -------------------
autoencoder = LitAutoEncoder()
trainer = L.Trainer()
trainer.fit(autoencoder, data.DataLoader(train), data.DataLoader(val))

pip install torchvision
python main.py

# 8 GPUs
# no code changes needed
trainer = Trainer(accelerator="gpu", devices=8)

# 256 GPUs
trainer = Trainer(accelerator="gpu", devices=8, num_nodes=32)

# no code changes needed
trainer = Trainer(accelerator="tpu", devices=8)

# no code changes needed
trainer = Trainer(precision=16)

from lightning import loggers

# litlogger
trainer = Trainer(logger=LitLogger())

# tensorboard
trainer = Trainer(logger=TensorBoardLogger("logs/"))

# weights and biases
trainer = Trainer(logger=loggers.WandbLogger())

# comet
trainer = Trainer(logger=loggers.CometLogger())

# mlflow
trainer = Trainer(logger=loggers.MLFlowLogger())

# neptune
trainer = Trainer(logger=loggers.NeptuneLogger())

# ... and dozens more

es = EarlyStopping(monitor="val_loss")
trainer = Trainer(callbacks=[es])

checkpointing = ModelCheckpoint(monitor="val_loss")
trainer = Trainer(callbacks=[checkpointing])

# torchscript
autoencoder = LitAutoEncoder()
torch.jit.save(autoencoder.to_torchscript(), "model.pt")

# onnx
with tempfile.NamedTemporaryFile(suffix=".onnx", delete=False) as tmpfile:
    autoencoder = LitAutoEncoder()
    input_sample = torch.randn((1, 64))
    autoencoder.to_onnx(tmpfile.name, input_sample, export_params=True)
    os.path.isfile(tmpfile.name)

+ import lightning as L
  import torch; import torchvision as tv

 dataset = tv.datasets.CIFAR10("data", download=True,
                               train=True,
                               transform=tv.transforms.ToTensor())

+ fabric = L.Fabric()
+ fabric.launch()

  model = tv.models.resnet18()
  optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
- device = "cuda" if torch.cuda.is_available() else "cpu"
- model.to(device)
+ model, optimizer = fabric.setup(model, optimizer)

  dataloader = torch.utils.data.DataLoader(dataset, batch_size=8)
+ dataloader = fabric.setup_dataloaders(dataloader)

  model.train()
  num_epochs = 10
  for epoch in range(num_epochs):
      for batch in dataloader:
          inputs, labels = batch
-         inputs, labels = inputs.to(device), labels.to(device)
          optimizer.zero_grad()
          outputs = model(inputs)
          loss = torch.nn.functional.cross_entropy(outputs, labels)
-         loss.backward()
+         fabric.backward(loss)
          optimizer.step()
          print(loss.data)

import lightning as L
import torch; import torchvision as tv

dataset = tv.datasets.CIFAR10("data", download=True,
                              train=True,
                              transform=tv.transforms.ToTensor())

fabric = L.Fabric()
fabric.launch()

model = tv.models.resnet18()
optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
model, optimizer = fabric.setup(model, optimizer)

dataloader = torch.utils.data.DataLoader(dataset, batch_size=8)
dataloader = fabric.setup_dataloaders(dataloader)

model.train()
num_epochs = 10
for epoch in range(num_epochs):
    for batch in dataloader:
        inputs, labels = batch
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = torch.nn.functional.cross_entropy(outputs, labels)
        fabric.backward(loss)
        optimizer.step()
        print(loss.data)

# Use your available hardware
# no code changes needed
fabric = Fabric()

# Run on GPUs (CUDA or MPS)
fabric = Fabric(accelerator="gpu")

# 8 GPUs
fabric = Fabric(accelerator="gpu", devices=8)

# 256 GPUs, multi-node
fabric = Fabric(accelerator="gpu", devices=8, num_nodes=32)

# Run on TPUs
fabric = Fabric(accelerator="tpu")

# Use state-of-the-art distributed training techniques
fabric = Fabric(strategy="ddp")
fabric = Fabric(strategy="deepspeed")
fabric = Fabric(strategy="fsdp")

# Switch the precision
fabric = Fabric(precision="16-mixed")
fabric = Fabric(precision="64")

  # no more of this!
- model.to(device)
- batch.to(device)

import lightning as L


class MyCustomTrainer:
    def __init__(self, accelerator="auto", strategy="auto", devices="auto", precision="32-true"):
        self.fabric = L.Fabric(accelerator=accelerator, strategy=strategy, devices=devices, precision=precision)

    def fit(self, model, optimizer, dataloader, max_epochs):
        self.fabric.launch()

        model, optimizer = self.fabric.setup(model, optimizer)
        dataloader = self.fabric.setup_dataloaders(dataloader)
        model.train()

        for epoch in range(max_epochs):
            for batch in dataloader:
                input, target = batch
                optimizer.zero_grad()
                output = model(input)
                loss = loss_fn(output, target)
                self.fabric.backward(loss)
                optimizer.step()