使用PyTorch构建神经网络的操作指南

pip install torch torchvision

import torch
# 创建一个未初始化的 5x3 矩阵
x = torch.empty(5, 3)
print(x)
# 创建一个随机初始化的 5x3 矩阵
x = torch.rand(5, 3)
print(x)
# 创建一个全部为 0，数据类型为 long 的矩阵
x = torch.zeros(5, 3, dtype=torch.long)
print(x)
# 创建 tensor 并直接使用数据初始化
x = torch.tensor([5.5, 3])
print(x)

import torch.nn as nn
import torch.nn.functional as F
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 输入图像为单通道，输出通道为 6，3x3 正方形卷积核
        self.conv1 = nn.Conv2d(1, 6, 3)
        self.conv2 = nn.Conv2d(6, 16, 3)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(16 * 6 * 6, 120)  # 6*6 是图像维度
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
    def forward(self, x):
        # 在 2x2 窗口上进行最大池化
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2))
        # 如果是方阵，只需要指定一个数字
        x = F.max_pool2d(F.relu(self.conv2(x)), 2)
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    def num_flat_features(self, x):
        size = x.size()[1:]  # 所有维度除了批量维度
        num_features = 1
        for s in size:
            num_features *= s
        return num_features
net = Net()
print(net)