本文正在参加「金石计划 . 分割6万现金大奖」
作者简介：秃头小苏，致力于用最通俗的语言描述问题
专栏引荐：深度学习网络原理与实战
近期目标：写好专栏的每一篇文章
支撑小苏：点赞、收藏⭐、留言
pytorch中Tensorboard的运用
写在前面
近期我计划不定期更新一些pytorch的教程，记录一些经常遇到的办法，避免每次遇到后重复搜索浪费时间，在之前我首要写过两篇pytorch教材，感兴趣的能够看一下，别离如下：
- pytorch中的transforms.ToTensor和transforms.Normalize了解
- pytorch模型保存、加载与续练习
本期为咱们带来Tensorborad的运用，同样，本篇基于Pytorch官网为咱们介绍，同时参加自己的了解，希望咱们阅读后能够有所收获。
准备好了的话，就让咱们开端吧！！！
导入相关包
首要咱们需求导入相关包，针对这节内容最重要的包就是SummaryWriter这个啦，咱们没有装置Tensorboard记得先装置喔，怎样装置就不用我教了吧，咱们动动勤快的小手儿百度一下，然后敲个指令就好咯。
# PyTorch model and training necessities
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
# Image datasets and image manipulation
import torchvision
import torchvision.transforms as transforms
# Image display
import matplotlib.pyplot as plt
import numpy as np
# PyTorch TensorBoard support
from torch.utils.tensorboard import SummaryWriter
加载数据集
本次运用的数据集是FashionMNIST数据集，它和MNIST数据集很像，都是单通道的2828巨细的图片，图片内容是各种衣服、鞋等一系列服饰。数据集加载的进程很简单，就不介绍了哈，不清楚这些的能够看看我往期的文章。需求留意的是官网运用DataLoader办法时num_workers设置为2，如果你运用CPU练习或许调试的话，请务必将num_workers设置为0。
# Gather datasets and prepare them for consumption
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))])
# Store separate training and validations splits in ./data
training_set = torchvision.datasets.FashionMNIST('./data',
download=True,
train=True,
transform=transform)
validation_set = torchvision.datasets.FashionMNIST('./data',
download=True,
train=False,
transform=transform)
training_loader = torch.utils.data.DataLoader(training_set,
batch_size=4,
shuffle=True,
num_workers=0)
validation_loader = torch.utils.data.DataLoader(validation_set,
batch_size=4,
shuffle=False,
num_workers=0)
运用matplotlib可视化图片
咱们先来运用matplotlib展示一下图片，咱们将其保存到result文件夹下，能够来看一下成果。
# Extract a batch of 4 images
dataiter = iter(training_loader)
images, labels = next(dataiter)
# Create a grid from the images and show them
img_grid = torchvision.utils.make_grid(images)
torchvision.utils.save_image(img_grid, "./result/img_grid.bmp")
运用Tensorboard可视化图片
首要咱们需求通过SummaryWriter发动Tensorboard，后边的'runs/fashion_mnist_experiment_1'为文件保存路径，接着咱们运用add_image添加图片。flush()办法是为了确保文件写入磁盘。
# Default log_dir argument is "runs" - but it's good to be specific
# torch.utils.tensorboard.SummaryWriter is imported above
writer = SummaryWriter('runs/fashion_mnist_experiment_1')
# Write image data to TensorBoard log dir
writer.add_image('Four Fashion-MNIST Images', img_grid)
writer.flush()
# To view, start TensorBoard on the command line with:
# tensorboard --logdir=runs
# ...and open a browser tab to http://localhost:6006/
履行完指令后，咱们能够在中止敲 tensorboard --logdir=runs，其中runs为保存的路径，如下图所示：
此刻咱们进入http://localhost:6006/即可检查图片，如下图所示：
运用Tensorboard可视化模型
首要咱们来创建模型一个简单的模型，如下：
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 4 * 4, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 4 * 4)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
这里咱们的数据集用到仍然是FashionMNIST，可视化模型用到的函数为add_graph()，其余部分根本和可视化图片共同。
# Again, grab a single mini-batch of images
dataiter = iter(training_loader)
images, labels = next(dataiter)
writer = SummaryWriter('runs/fashion_mnist_experiment_1')
# add_graph() will trace the sample input through your model,
# and render it as a graph.
writer.add_graph(net, images)
writer.flush()
此部分代码履行完成之后，改写一下http://localhost:6006/ 这个网址，会出现一个GRAPHS列，里边保存了刚刚定义网络的信息。咱们能够简单看一下，如下图所示：
运用Tensorboard可视化丢失
此阶段模型选用的和上一末节共同。直接上练习代码吧，如下：
print(len(validation_loader))
for epoch in range(1): # loop over the dataset multiple times
running_loss = 0.0
for i, data in enumerate(training_loader, 0):
# basic training loop
inputs, labels = data
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 1000 == 999: # Every 1000 mini-batches...
print('Batch {}'.format(i + 1))
# Check against the validation set
running_vloss = 0.0
net.train(False) # Don't need to track gradents for validation
for j, vdata in enumerate(validation_loader, 0):
vinputs, vlabels = vdata
voutputs = net(vinputs)
vloss = criterion(voutputs, vlabels)
running_vloss += vloss.item()
net.train(True) # Turn gradients back on for training
avg_loss = running_loss / 1000
avg_vloss = running_vloss / len(validation_loader)
# Log the running loss averaged per batch
writer.add_scalars('Training vs. Validation Loss',
{ 'Training' : avg_loss, 'Validation' : avg_vloss },
epoch * len(training_loader) + i)
running_loss = 0.0
print('Finished Training')
writer.flush()
保存练习丢失所用的函数为add_scalars，其余部分也大差不差，咱们此刻改写http://localhost:6006/ 网页，会得到练习丢失和验证丢失，如下图所示：
小结
是不是发现这部分还挺好玩的呢，快去试试吧。最后我想说一下在jupyter notebook或许google clab中怎样发动Tensorboard，也很简单，分两步，如下：
%load_ext tensorboard%tensorboard --logdir logs
履行上述两行代码就能够直接在jupyter notebook或许google clab运用Tensorboard啦，去尝试尝试吧！！！
如若文章对你有所协助，那就
