使用pytorch需要python环境，建议是直接装anaconda ，IDE用visual studio
anaconda安装
Anaconda 是一个用于科学计算的 Python 发行版，支持 Linux, Mac, Windows, 包含了众多流行的科学计算、数据分析的 Python 包
官网链接anaconda
本人下载：Anaconda3-2023.03-1-Windows-x86_64.exe 内置python 3.10
双击exe一键安装，安装好后可以通过anaconda navigator查看已安装的包
可以通过 Start - Anaconda3 - Anaconda PowerShell Prompt查看安装版本
pytorch 安装
官网
quick start guide
按需选择配置获取安装cmd，推荐windows下配置如下
PyTorch build – stable.
Your OS – Windows
Package – Conda
Language – Python
Compute Platform – CPU, 或者根据你Cuda版本选择合适的compute platform
cuda版本可以点nvdia系统配置从driver处看，比如下图第三行显示是11.6
也可以命令行运行nvdia-smi获取信息。
在 Anaconda prompt 命令窗口中输入cmd 开始安装 eg： conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia
安装结束确认
pytorch 使用
以图片分类demo为例使用pytorch
-
visual studio 创建新project
-
点Create a new project后选择Python Application，新建python项目，（直接运行项目等上传后贴链接 点击这里）
-
配置环境，添加环境选现有环境，如果默认没出来anaconda，就自定义环境，把anaconda所在路径添加进去，vs会自动识别，确认添加即可
-
demo正文开始，先load 数据集
load CIFAR10, 第一次加载需要比较多的时间
from torchvision.datasets import CIFAR10
from torchvision.transforms import transforms
from torch.utils.data import DataLoader
# Loading and normalizing the data.
# Define transformations for the training and test sets
transformations = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# CIFAR10 dataset consists of 50K training images. We define the batch size of 10 to load 5,000 batches of images.
batch_size = 10
number_of_labels = 10
# Create an instance for training.
# When we run this code for the first time, the CIFAR10 train dataset will be downloaded locally.
train_set =CIFAR10(root="./data",train=True,transform=transformations,download=True)
# Create a loader for the training set which will read the data within batch size and put into memory.
train_loader = DataLoader(train_set, batch_size=batch_size, shuffle=True, num_workers=0)
print("The number of images in a training set is: ", len(train_loader)*batch_size)
# Create an instance for testing, note that train is set to False.
# When we run this code for the first time, the CIFAR10 test dataset will be downloaded locally.
test_set = CIFAR10(root="./data", train=False, transform=transformations, download=True)
# Create a loader for the test set which will read the data within batch size and put into memory.
# Note that each shuffle is set to false for the test loader.
test_loader = DataLoader(test_set, batch_size=batch_size, shuffle=False, num_workers=0)
print("The number of images in a test set is: ", len(test_loader)*batch_size)
print("The number of batches per epoch is: ", len(train_loader))
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
再定义CNN网络，（也可以用别的网络，以CNN为例）
Conv -> BatchNorm -> ReLU -> Conv -> BatchNorm -> ReLU -> MaxPool -> Conv -> BatchNorm -> ReLU -> Conv -> BatchNorm -> ReLU -> Linear.
import torch
import torch.nn as nn
import torchvision
import torch.nn.functional as F
# Define a convolution neural network
class Network(nn.Module):
def __init__(self):
super(Network, self).__init__()
self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=1)
self.bn1 = nn.BatchNorm2d(12)
self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(12)
self.pool = nn.MaxPool2d(2,2)
self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=1)
self.bn4 = nn.BatchNorm2d(24)
self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=1)
self.bn5 = nn.BatchNorm2d(24)
self.fc1 = nn.Linear(24*10*10, 10)
def forward(self, input):
output = F.relu(self.bn1(self.conv1(input)))
output = F.relu(self.bn2(self.conv2(output)))
output = self.pool(output)
output = F.relu(self.bn4(self.conv4(output)))
output = F.relu(self.bn5(self.conv5(output)))
output = output.view(-1, 24*10*10)
output = self.fc1(output)
return output
# Instantiate a neural network model
model = Network()
定义loss function
from torch.optim import Adam
# Define the loss function with Classification Cross-Entropy loss and an optimizer with Adam optimizer
loss_fn = nn.CrossEntropyLoss()
optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
训练function，可以自定义运行平台和训练参数
from torch.autograd import Variable
# Function to save the model
def saveModel():
path = "./myFirstModel.pth"
torch.save(model.state_dict(), path)
# Function to test the model with the test dataset and print the accuracy for the test images
def testAccuracy():
model.eval()
accuracy = 0.0
total = 0.0
with torch.no_grad():
for data in test_loader:
images, labels = data
# run the model on the test set to predict labels
outputs = model(images)
# the label with the highest energy will be our prediction
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
accuracy += (predicted == labels).sum().item()
# compute the accuracy over all test images
accuracy = (100 * accuracy / total)
return(accuracy)
# Training function. We simply have to loop over our data iterator and feed the inputs to the network and optimize.
def train(num_epochs):
best_accuracy = 0.0
# Define your execution device
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print("The model will be running on", device, "device")
# Convert model parameters and buffers to CPU or Cuda
model.to(device)
for epoch in range(num_epochs): # loop over the dataset multiple times
running_loss = 0.0
running_acc = 0.0
for i, (images, labels) in enumerate(train_loader, 0):
# get the inputs
images = Variable(images.to(device))
labels = Variable(labels.to(device))
# zero the parameter gradients
optimizer.zero_grad()
# predict classes using images from the training set
outputs = model(images)
# compute the loss based on model output and real labels
loss = loss_fn(outputs, labels)
# backpropagate the loss
loss.backward()
# adjust parameters based on the calculated gradients
optimizer.step()
# Let's print statistics for every 1,000 images
running_loss += loss.item() # extract the loss value
if i % 1000 == 999:
# print every 1000 (twice per epoch)
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 1000))
# zero the loss
running_loss = 0.0
# Compute and print the average accuracy fo this epoch when tested over all 10000 test images
accuracy = testAccuracy()
print('For epoch', epoch+1,'the test accuracy over the whole test set is %d %%' % (accuracy))
# we want to save the model if the accuracy is the best
if accuracy > best_accuracy:
saveModel()
best_accuracy = accuracy
结合数据集进行训练
import matplotlib.pyplot as plt
import numpy as np
# Function to show the images
def imageshow(img):
img = img / 2 + 0.5 # unnormalize
npimg = img.numpy()
plt.imshow(np.transpose(npimg, (1, 2, 0)))
plt.show()
# Function to test the model with a batch of images and show the labels predictions
def testBatch():
# get batch of images from the test DataLoader
images, labels = next(iter(test_loader))
# show all images as one image grid
imageshow(torchvision.utils.make_grid(images))
# Show the real labels on the screen
print('Real labels: ', ' '.join('%5s' % classes[labels[j]]
for j in range(batch_size)))
# Let's see what if the model identifiers the labels of those example
outputs = model(images)
# We got the probability for every 10 labels. The highest (max) probability should be correct label
_, predicted = torch.max(outputs, 1)
# Let's show the predicted labels on the screen to compare with the real ones
print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
for j in range(batch_size)))
看每个class分类准确度，该函数可加可不加
# Function to test what classes performed well
def testClassess():
class_correct = list(0. for i in range(number_of_labels))
class_total = list(0. for i in range(number_of_labels))
with torch.no_grad():
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs, 1)
c = (predicted == labels).squeeze()
for i in range(batch_size):
label = labels[i]
class_correct[label] += c[i].item()
class_total[label] += 1
for i in range(number_of_labels):
print('Accuracy of %5s : %2d %%' % (
classes[i], 100 * class_correct[i] / class_total[i]))
主函数
if __name__ == "__main__":
# Let's build our model
train(5)
print('Finished Training')
# Test which classes performed well
testClassess()
# Let's load the model we just created and test the accuracy per label
model = Network()
path = "myFirstModel.pth"
model.load_state_dict(torch.load(path))
# Test with batch of images
testBatch()
运行结果如下
项目已打包：下载
Ref：
https://learn.microsoft.com/zh-cn/visualstudio/python/managing-python-environments-in-visual-studio?view=vs-2022#selecting-and-installing-python-interpreters
https://learn.microsoft.com/en-us/windows/ai/windows-ml/tutorials/pytorch-train-model
