PyTorch的TensorBoard用法示例

原文： https://www.emperinter.info/2020/07/30/tensorboard-in-pytorch/

缘由

自己上次安装好PyTorch以及训练了一下官方的数据，今天看到了这个TensorBoard来可视化的用法，感觉不错就尝试玩了一下！自己只是尝试了一下追踪模型训练的过程，其他自己去看官网教程吧！

用法

具体详细说明请参考https://pytorch.org/tutorials/intermediate/tensorboard_tutorial.html

简单说就是：

• 设置TensorBoard。

• 写入TensorBoard。

• 运行

• 打开http://localhost:6006/

例子

我把训练的图片分类的loss用tensorboard给可视化出来了：

步骤

• 设置TensorBoard。

简单说是设置基本tensorboard运行需要的东西，我这代码中的imshow(img)和matplotlib_imshow(img, one_channel=False)都是显示图片的函数，可以统一替换，我自己测试就没改了！

# helper function to show an image
# (used in the `plot_classes_preds` function below)
def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5     # unnormalize
    npimg = img.cpu().numpy()
    if one_channel:
        plt.imshow(npimg, cmap="Greys")
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))    

# 设置tensorBoard
# default `log_dir` is "runs" - we'll be more specific here
writer = SummaryWriter('runs/image_classify_tensorboard')

# 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)
imshow(img_grid)

# write to tensorboard
writer.add_image('imag_classify', img_grid)

# Tracking model training with TensorBoard
# helper functions

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())
    preds = np.squeeze(preds_tensor.cpu().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

• 写入TensorBoard。

这个在训练的每一阶段写入tensorboard

        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))

            # 把数据写入tensorflow
            # ...log the running loss
            writer.add_scalar('image training loss',
                            running_loss / 2000,
                            epoch * len(trainloader) + i)

            # ...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)

• 运行

tensorboard --logdir=runs

• 打开http://localhost:6006/ 即可查看

完整版代码参考

如需了解完整代码请访问：https://www.emperinter.info/2020/07/30/tensorboard-in-pytorch/

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from datetime import datetime
from torch.utils.tensorboard import SummaryWriter
..............
..............
..............

参考

• 用PyTorch训练一个图像分类
• TypeError: can’t convert CUDA tensor to numpy. Use Tensor.cpu() to copy the tensor to host memory first