本文记录了pytorch训练可视化的内容，分别用matplotlib和tensorboard实现，内容比较简单，适合入门，博客记录在此，仅备今后之用。
参考博客：
pytorch使用matplotlib和tensorboard实现模型和训练的可视化_踏莎行的博客-CSDN博客
python中的matplotlib用法_Great haste makes great waste-CSDN博客
【tensorboard官方dome】Visualizing Models, Data, and Training with TensorBoard — PyTorch Tutorials 1.9.0+cu102 documentation
1.matplotlib
安装matplotlib包
pip install matplotlib
引入模块
import matplotlib.pyplot as plt
用plot绘图函数
tran_ls.append(running_loss / 500)
plt.plot(range(len(tran_ls)) ,tran_ls,color="red")
plt.xlabel("epoch")
plt.ylabel("loss")
plt.show()
喜闻乐见的代码：
import torch
import torchvision
import torch.optim as optim
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torch.nn as nn
import torch.nn.functional as F
import matplotlib.pyplot as plt
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 16, 5)
self.pool1 = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(16, 32, 5)
self.pool2 = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(32*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = F.relu(self.conv1(x)) # input(3, 32, 32) output(16, 28, 28)
x = self.pool1(x) # output(16, 14, 14)
x = F.relu(self.conv2(x)) # output(32, 10, 10)
x = self.pool2(x) # output(32, 5, 5)
x = x.view(-1, 32*5*5) # output(32*5*5)
x = F.relu(self.fc1(x)) # output(120)
x = F.relu(self.fc2(x)) # output(84)
x = self.fc3(x) # output(10)
return x
# define draw
# def plotCurve(x_vals,
# x_label, y_label,
# x2_vals=None,
# legend=None,
# figsize=(3.5, 2.5)):
# # set figsize
# plt.xlabel(x_label)
# plt.ylabel(y_label)
# plt.semilogy(x_vals)
# if x2_vals:
# plt.semilogy(x2_vals, linestyle=':')
# if legend:
# plt.legend(legend)
def main():
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=True, num_workers=0)
# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)
val_image, val_label = val_data_iter.next()
# classes = ('plane', 'car', 'bird', 'cat',
# 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
net = LeNet()
# get some random training images
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
tran_ls = []
for epoch in range(5): # loop over the dataset multiple times
running_loss = 0.0
for step, data in enumerate(train_loader, start=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 = loss_function(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if step % 500 == 499: # print every 500 mini-batches
with torch.no_grad():
outputs = net(val_image) # [batch, 10]
predict_y = torch.max(outputs, dim=1)[1]
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)
print('[%d, %5d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
tran_ls.append(running_loss / 500)
running_loss = 0.0
plt.plot(range(len(tran_ls)) ,tran_ls,color="red")
plt.xlabel("epoch")
plt.ylabel("loss")
plt.show()
print('Finished Training')
save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)
if __name__ == '__main__':
main()
2.tensorboard
安装tensorboard包
pip install tensorboard
引入模块
from torch.utils.tensorboard import SummaryWriter
实例化SummaryWriter对象
writer = SummaryWriter("runs/cifar10_experiment")
命令行启动tensorboard网页，打开网址进入tensorboard主页面
tensorboard --logdir=runs
模型可视化，tensorboard可以通过传入一个样本，写入graph到日志中，在网页上看到模型的结构
# get some random training images trainloader=train_loader dataiter = iter(trainloader) # # create grid of images # img_grid = torchvision.utils.make_grid(images) images, labels = dataiter.next() writer.add_graph(net, images)
刷新页面即可看到模型
喜闻乐见的代码环节
import torch
import torchvision
import torch.optim as optim
import torchvision.transforms as transforms
from torch.utils.tensorboard import SummaryWriter
import torch.nn as nn
import torch.nn.functional as F
writer = SummaryWriter("runs/cifar10_experiment")
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv1 = nn.Conv2d(3, 16, 5)
self.pool1 = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(16, 32, 5)
self.pool2 = nn.MaxPool2d(2, 2)
self.fc1 = nn.Linear(32*5*5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = F.relu(self.conv1(x)) # input(3, 32, 32) output(16, 28, 28)
x = self.pool1(x) # output(16, 14, 14)
x = F.relu(self.conv2(x)) # output(32, 10, 10)
x = self.pool2(x) # output(32, 5, 5)
x = x.view(-1, 32*5*5) # output(32*5*5)
x = F.relu(self.fc1(x)) # output(120)
x = F.relu(self.fc2(x)) # output(84)
x = self.fc3(x) # output(10)
return x
def main():
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 50000张训练图片
# 第一次使用时要将download设置为True才会自动去下载数据集
train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
shuffle=True, num_workers=0)
# 10000张验证图片
# 第一次使用时要将download设置为True才会自动去下载数据集
val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
shuffle=False, num_workers=0)
val_data_iter = iter(val_loader)
val_image, val_label = val_data_iter.next()
# classes = ('plane', 'car', 'bird', 'cat',
# 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
net = LeNet()
# get some random training images
trainloader=train_loader
dataiter = iter(trainloader)
# # create grid of images
# img_grid = torchvision.utils.make_grid(images)
images, labels = dataiter.next()
writer.add_graph(net, images)
loss_function = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
for epoch in range(20): # loop over the dataset multiple times
running_loss = 0.0
for step, data in enumerate(train_loader, start=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 = loss_function(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.item()
if step % 500 == 499: # print every 500 mini-batches
with torch.no_grad():
outputs = net(val_image) # [batch, 10]
predict_y = torch.max(outputs, dim=1)[1]
accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)
print('[%d, %5d] train_loss: %.3f test_accuracy: %.3f' %
(epoch + 1, step + 1, running_loss / 500, accuracy))
writer.add_scalar('training loss',
running_loss / 500,
epoch )
running_loss = 0.0
print('Finished Training')
save_path = './Lenet.pth'
torch.save(net.state_dict(), save_path)
if __name__ == '__main__':
main()
