pytorch_lightning 使用教程

安装测试1

我在124服务器上尝试安装pytorch_lightning1.2.10
conda create -n pylight python3.6.10
pip install pytorch-lightning==1.2.10

安装

提前安装好pytorch

pip install pytorch-lightning

我的环境如下
pip install torchvision

学习案例1

import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE" ## 这里需要注意,我的mac运行pytorch，必须提前添加，否认内核直接崩掉
import pandas as pd
import seaborn as sn
import torch
from IPython.core.display import display
from pytorch_lightning import LightningModule, Trainer
from pytorch_lightning.callbacks.progress import TQDMProgressBar
from pytorch_lightning.loggers import CSVLogger
from torch import nn
from torch.nn import functional as F
from torch.utils.data import DataLoader, random_split
from torchmetrics import Accuracy
from torchvision import transforms
from torchvision.datasets import MNIST

PATH_DATASETS = os.environ.get("PATH_DATASETS", ".")
BATCH_SIZE = 256 if torch.cuda.is_available() else 64

class MNISTModel(LightningModule):
    def __init__(self):
        super().__init__()
        self.l1 = torch.nn.Linear(28 * 28, 10)

    def forward(self, x):
        return torch.relu(self.l1(x.view(x.size(0), -1)))

    def training_step(self, batch, batch_nb):
        x, y = batch
        loss = F.cross_entropy(self(x), y)
        return loss

    def configure_optimizers(self):
        return torch.optim.Adam(self.parameters(), lr=0.02)

# Init our model
mnist_model = MNISTModel()

# Init DataLoader from MNIST Dataset
train_ds = MNIST(PATH_DATASETS, train=True, download=True, transform=transforms.ToTensor())
train_loader = DataLoader(train_ds, batch_size=BATCH_SIZE)

# Initialize a trainer
trainer = Trainer(
    accelerator="auto",
    devices=1 if torch.cuda.is_available() else None,  # limiting got iPython runs
    max_epochs=3,
    callbacks=[TQDMProgressBar(refresh_rate=20)],
)

# Train the model ⚡
trainer.fit(mnist_model, train_loader)

结果如下

example2

class LitMNIST(LightningModule):
    def __init__(self, data_dir=PATH_DATASETS, hidden_size=64, learning_rate=2e-4):

        super().__init__()

        # Set our init args as class attributes
        self.data_dir = data_dir
        self.hidden_size = hidden_size
        self.learning_rate = learning_rate

        # Hardcode some dataset specific attributes
        self.num_classes = 10
        self.dims = (1, 28, 28)
        channels, width, height = self.dims
        self.transform = transforms.Compose(
            [
                transforms.ToTensor(),
                transforms.Normalize((0.1307,), (0.3081,)),
            ]
        )

        # Define PyTorch model
        self.model = nn.Sequential(
            nn.Flatten(),
            nn.Linear(channels * width * height, hidden_size),
            nn.ReLU(),
            nn.Dropout(0.1),
            nn.Linear(hidden_size, hidden_size),
            nn.ReLU(),
            nn.Dropout(0.1),
            nn.Linear(hidden_size, self.num_classes),
        )

        self.val_accuracy = Accuracy()
        self.test_accuracy = Accuracy()

    def forward(self, x):
        x = self.model(x)
        return F.log_softmax(x, dim=1)

    def training_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = F.nll_loss(logits, y)
        return loss

    def validation_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = F.nll_loss(logits, y)
        preds = torch.argmax(logits, dim=1)
        self.val_accuracy.update(preds, y)

        # Calling self.log will surface up scalars for you in TensorBoard
        self.log("val_loss", loss, prog_bar=True)
        self.log("val_acc", self.val_accuracy, prog_bar=True)

    def test_step(self, batch, batch_idx):
        x, y = batch
        logits = self(x)
        loss = F.nll_loss(logits, y)
        preds = torch.argmax(logits, dim=1)
        self.test_accuracy.update(preds, y)

        # Calling self.log will surface up scalars for you in TensorBoard
        self.log("test_loss", loss, prog_bar=True)
        self.log("test_acc", self.test_accuracy, prog_bar=True)

    def configure_optimizers(self):
        optimizer = torch.optim.Adam(self.parameters(), lr=self.learning_rate)
        return optimizer

    ####################
    # DATA RELATED HOOKS
    ####################

    def prepare_data(self):
        # download
        MNIST(self.data_dir, train=True, download=True)
        MNIST(self.data_dir, train=False, download=True)

    def setup(self, stage=None):

        # Assign train/val datasets for use in dataloaders
        if stage == "fit" or stage is None:
            mnist_full = MNIST(self.data_dir, train=True, transform=self.transform)
            self.mnist_train, self.mnist_val = random_split(mnist_full, [55000, 5000])

        # Assign test dataset for use in dataloader(s)
        if stage == "test" or stage is None:
            self.mnist_test = MNIST(self.data_dir, train=False, transform=self.transform)

    def train_dataloader(self):
        return DataLoader(self.mnist_train, batch_size=BATCH_SIZE)

    def val_dataloader(self):
        return DataLoader(self.mnist_val, batch_size=BATCH_SIZE)

    def test_dataloader(self):
        return DataLoader(self.mnist_test, batch_size=BATCH_SIZE)

model = LitMNIST()
trainer = Trainer(
    accelerator="auto",
    devices=1 if torch.cuda.is_available() else None,  # limiting got iPython runs
    max_epochs=3,
    callbacks=[TQDMProgressBar(refresh_rate=20)],
    logger=CSVLogger(save_dir="logs/"),
)
trainer.fit(model)
trainer.test()
trainer.fit(model)

metrics = pd.read_csv(f"{trainer.logger.log_dir}/metrics.csv")
del metrics["step"]
metrics.set_index("epoch", inplace=True)
display(metrics.dropna(axis=1, how="all").head())
sn.relplot(data=metrics, kind="line")