TensorboardX绘制Pytorch神经网络结构图踩坑笔记

import torch
import torch.nn as nn
from tensorboardX import SummaryWriter

cfg = {
    'VGG11': [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'VGG13': [64, 64, 'M', 128, 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M'],
    'VGG16': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512, 'M', 512, 512, 512, 'M'],
    'VGG19': [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 256, 'M', 512, 512, 512, 512, 'M', 512, 512, 512, 512, 'M'],
}


# 模型需继承nn.Module
class VGG(nn.Module):
    # 初始化参数：
    def __init__(self, vgg_name):
        super(VGG, self).__init__()
        self.features = self._make_layers(cfg[vgg_name])
        self.classifier = nn.Sequential(
            nn.Linear(23040, 1024),
            nn.Linear(1024, 1),
            nn.Sigmoid()
        )

    # 模型计算时的前向过程，也就是按照这个过程进行计算
    def forward(self, x):
        out = self.features(x)
        out = out.view(out.size(0), -1)
        out = self.classifier(out)
        return out

    def _make_layers(self, cfg):
        layers = []
        in_channels = 1
        for x in cfg:
            if x == 'M':
                layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
            else:
                layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
                           nn.BatchNorm2d(x),
                           nn.ReLU(inplace=True)]
                in_channels = x
        layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
        return nn.Sequential(*layers)

dummy_input = torch.rand(1, 1, 484, 100)
model = VGG('VGG19')
with SummaryWriter(comment='VGG19') as w:
    w.add_graph(model, (dummy_input,))
print("finish")

代码demo如上，会自动生成文件

打开anaconda prompt

tensorboard --logdir="文件地址" --host=127.0.0.1