Documentation
中文 (简体)
搜索文档…
⌃K

PyTorch Ignite

Ignite支持Weights&Biases处理器(handler),在训练和验证过程中记录指标、模型参数/优化器参数、梯度。还可用来记录模型检查点并保存至Weights&Biases云。这个类同时也是权阈(wandb)模块的一个封装器。这就是说你可以用这个封装器调用所有wandb的函数。 请看关于如何保存模型参数和梯度的示例。

PyTorch的基础设置

from argparse import ArgumentParser
import wandb
import torch
from torch import nn
from torch.optim import SGD
from torch.utils.data import DataLoader
import torch.nn.functional as F
from torchvision.transforms import Compose, ToTensor, Normalize
from torchvision.datasets import MNIST
from ignite.engine import Events, create_supervised_trainer, create_supervised_evaluator
from ignite.metrics import Accuracy, Loss
from tqdm import tqdm
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
self.conv2_drop = nn.Dropout2d()
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=-1)
def get_data_loaders(train_batch_size, val_batch_size):
data_transform = Compose([ToTensor(), Normalize((0.1307,), (0.3081,))])
train_loader = DataLoader(MNIST(download=True, root=".", transform=data_transform, train=True),
batch_size=train_batch_size, shuffle=True)
val_loader = DataLoader(MNIST(download=False, root=".", transform=data_transform, train=False),
batch_size=val_batch_size, shuffle=False)
return train_loader, val_loader
在Ignite中使用WandBLogger,分为两个模块化过程:首先,需要创建一个WandBLogger对象。随后,该对象可被附加到任何训练器(trainer)或评估器(evaluator),以自动记录指标。我们将依次执行以下任务:1)创建一个WandBLogger对象;2)把该对象附加到输出处理器上,以:
  • 记录训练损失——附加到训练器上。
  • 记录验证损失——附加到评估器上
  • 记录可选参数——比如学习率。
  • 观察模型。
from ignite.contrib.handlers.wandb_logger import *
def run(train_batch_size, val_batch_size, epochs, lr, momentum, log_interval):
train_loader, val_loader = get_data_loaders(train_batch_size, val_batch_size)
model = Net()
device = 'cpu'
if torch.cuda.is_available():
device = 'cuda'
optimizer = SGD(model.parameters(), lr=lr, momentum=momentum)
trainer = create_supervised_trainer(model, optimizer, F.nll_loss, device=device)
evaluator = create_supervised_evaluator(model,
metrics={'accuracy': Accuracy(),
'nll': Loss(F.nll_loss)},
device=device)
desc = "ITERATION - loss: {:.2f}"
pbar = tqdm(
initial=0, leave=False, total=len(train_loader),
desc=desc.format(0)
)
#WandBlogger Object Creation
wandb_logger = WandBLogger(
project="pytorch-ignite-integration",
name="cnn-mnist",
config={"max_epochs": epochs,"batch_size":train_batch_size},
tags=["pytorch-ignite", "minst"]
)
wandb_logger.attach_output_handler(
trainer,
event_name=Events.ITERATION_COMPLETED,
tag="training",
output_transform=lambda loss: {"loss": loss}
)
wandb_logger.attach_output_handler(
evaluator,
event_name=Events.EPOCH_COMPLETED,
tag="training",
metric_names=["nll", "accuracy"],
global_step_transform=lambda *_: trainer.state.iteration,
)
wandb_logger.attach_opt_params_handler(
trainer,
event_name=Events.ITERATION_STARTED,
optimizer=optimizer,
param_name='lr' # optional
)
wandb_logger.watch(model)
根据需要,我们还可以利用Ignite的EVENTS直接把指标记录到终端。
@trainer.on(Events.ITERATION_COMPLETED(every=log_interval))
def log_training_loss(engine):
pbar.desc = desc.format(engine.state.output)
pbar.update(log_interval)
@trainer.on(Events.EPOCH_COMPLETED)
def log_training_results(engine):
pbar.refresh()
evaluator.run(train_loader)
metrics = evaluator.state.metrics
avg_accuracy = metrics['accuracy']
avg_nll = metrics['nll']
tqdm.write(
"Training Results - Epoch: {} Avg accuracy: {:.2f} Avg loss: {:.2f}"
.format(engine.state.epoch, avg_accuracy, avg_nll)
)
@trainer.on(Events.EPOCH_COMPLETED)
def log_validation_results(engine):
evaluator.run(val_loader)
metrics = evaluator.state.metrics
avg_accuracy = metrics['accuracy']
avg_nll = metrics['nll']
tqdm.write(
"Validation Results - Epoch: {} Avg accuracy: {:.2f} Avg loss: {:.2f}"
.format(engine.state.epoch, avg_accuracy, avg_nll))
pbar.n = pbar.last_print_n = 0
trainer.run(train_loader, max_epochs=epochs)
pbar.close()
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument('--batch_size', type=int, default=64,
help='input batch size for training (default: 64)')
parser.add_argument('--val_batch_size', type=int, default=1000,
help='input batch size for validation (default: 1000)')
parser.add_argument('--epochs', type=int, default=10,
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01,
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5,
help='SGD momentum (default: 0.5)')
parser.add_argument('--log_interval', type=int, default=10,
help='how many batches to wait before logging training status')
args = parser.parse_args()
run(args.batch_size, args.val_batch_size, args.epochs, args.lr, args.momentum, args.log_interval)
运行以上代码后,我们得到下列可视化结果:
更详细的文档请参考 Ignite文档