Build and Train a Model¶
Required background: Basic Python familiarity and complete the guide.
Goal: We’ll walk you through the creation of a model using PyTorch Lightning.
A simple PyTorch Lightning script¶
Let’s assume you already have a folder with those two files.
pl_project/
train.py # your own script to train your models
requirements.txt # your python requirements.
If you don’t, simply create a pl_project
folder with those two files and add the following PyTorch Lightning code in the train.py
file. This code trains a simple AutoEncoder
on MNIST Dataset.
import os
import torch
import torch.nn.functional as F
from torch import nn
from torch.utils.data import DataLoader, random_split
from torchvision import transforms as T
from torchvision.datasets import MNIST
import pytorch_lightning as pl
class LitAutoEncoder(pl.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, y = 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
dataset = MNIST(os.getcwd(), download=True, transform=T.ToTensor())
train, val = random_split(dataset, [55000, 5000])
autoencoder = LitAutoEncoder()
trainer = pl.Trainer(accelerator="auto")
trainer.fit(autoencoder, DataLoader(train), DataLoader(val))
Add the following to the requirements.txt
file.
torch
torchvision
pytorch_lightning
Simply run the following commands in your terminal to install the requirements and train the model.
pip install -r requirements.txt
python train.py
Get through PyTorch Lightning Introduction to learn more.