PyTorch Tutorials 摘要(4) Visualizing models, data, and training with tensorboard

0. 前言

• 官方链接
• 本文目标：介绍PyTorch中Tensorboard的基本使用
• 本文主要内容
  • Tensorboard的基本使用（summary writer的创建，添加image）
  • Tensorboard展示模型结构
  • Tensorboard展示参数分布（high dimension用low dimension展示）
  • Tensorboard训练过程中的使用（展示loss与image预测结果）

1. 最简单的使用

• 作用：构建writer、写入图片。

# 构建 summary writer，设置文件路径
from torch.utils.tensorboard import SummaryWriter
# default `log_dir` is "runs" - we'll be more specific here
writer = SummaryWriter('runs/fashion_mnist_experiment_1')

# 将图片写入event文件中
# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()
# create grid of images
img_grid = torchvision.utils.make_grid(images)
# show images
matplotlib_imshow(img_grid, one_channel=True)
# write to tensorboard
writer.add_image('four_fashion_mnist_images', img_grid)

# 最终使用
# tensorboard --logdir /path/to/log

2. 查看模型结构

writer.add_graph(net, images)
writer.close()

3. 查看参数、变量的投影

• 使用 lower dimensional representation 来表示 higher dimensional data

# helper function
def select_n_random(data, labels, n=100):
    '''
    Selects n random datapoints and their corresponding labels from a dataset
    '''
    assert len(data) == len(labels)

    perm = torch.randperm(len(data))
    return data[perm][:n], labels[perm][:n]

# select random images and their target indices
images, labels = select_n_random(trainset.data, trainset.targets)

# get the class labels for each image
class_labels = [classes[lab] for lab in labels]

# log embeddings
features = images.view(-1, 28 * 28)
writer.add_embedding(features,
                    metadata=class_labels,
                    label_img=images.unsqueeze(1))
writer.close()

4. 记录训练过程

• 记录损失函数的变化。
• 偶尔放几张图片展示预测结果。

# 生成需要展示的图片
def images_to_probs(net, images):
    '''
    Generates predictions and corresponding probabilities from a trained
    network and a list of images
    '''
    output = net(images)
    # convert output probabilities to predicted class
    _, preds_tensor = torch.max(output, 1)
    preds = np.squeeze(preds_tensor.numpy())
    return preds, [F.softmax(el, dim=0)[i].item() for i, el in zip(preds, output)]
def plot_classes_preds(net, images, labels):
    '''
    Generates matplotlib Figure using a trained network, along with images
    and labels from a batch, that shows the network's top prediction along
    with its probability, alongside the actual label, coloring this
    information based on whether the prediction was correct or not.
    Uses the "images_to_probs" function.
    '''
    preds, probs = images_to_probs(net, images)
    # plot the images in the batch, along with predicted and true labels
    fig = plt.figure(figsize=(12, 48))
    for idx in np.arange(4):
        ax = fig.add_subplot(1, 4, idx+1, xticks=[], yticks=[])
        matplotlib_imshow(images[idx], one_channel=True)
        ax.set_title("{0}, {1:.1f}%\n(label: {2})".format(
            classes[preds[idx]],
            probs[idx] * 100.0,
            classes[labels[idx]]),
                    color=("green" if preds[idx]==labels[idx].item() else "red"))
    return fig

running_loss = 0.0
for epoch in range(1):  # loop over the dataset multiple times

    for i, data in enumerate(trainloader, 0):

        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 1000 == 999:    # every 1000 mini-batches...
            
            # 添加标量
            # ...log the running loss
            writer.add_scalar('training loss',
                            running_loss / 1000,
                            epoch * len(trainloader) + i)
            
            # 添加图片
            # ...log a Matplotlib Figure showing the model's predictions on a
            # random mini-batch
            writer.add_figure('predictions vs. actuals',
                            plot_classes_preds(net, inputs, labels),
                            global_step=epoch * len(trainloader) + i)
            running_loss = 0.0
print('Finished Training')