卷积神经网络的网络层与参数的解析

参考博主：https://blog.csdn.net/weixin_41457494/article/details/86238443

import torch
from torch.autograd import Variable
import torch.nn as nn
import torch.nn.functional as F
# 神经网络参数解析
'''
神经网络参数解析
'''
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        # 1 input image channel, 6 output channels, 5x5 square convolution
        # kernel
        self.conv1 = nn.Conv2d(1, 6, 2)
        # an affine operation: y = Wx + b
        self.fc1 = nn.Linear(6 * 3 * 3, 4)
    def forward(self, x):
        # Max pooling over a (2, 2) window
        print("x.size:{}".format(x.size()))
        x = F.max_pool2d(F.relu(self.conv1(x)), (2, 2),stride=1)
        print('================')
        print("x.size:{}".format(x.size()))
        x = x.view(-1, self.num_flat_features(x))
        x = F.relu(self.fc1(x))
        return x
    def num_flat_features(self, x):
        size = x.size()[1:]  # all dimensions except the batch dimension
        num_features = 1
        for s in size:
            num_features *= s
        return num_features

if __name__ =='__main__':
    net = Net()
#    print("net:{}".format(net))
#    print(net)
    params = list(net.parameters())
    print("创建的神经网络共有{}组参数\n".format(len(params)))

    print("卷积核的初始化参数：{}\n".format(params[0]))
    print("卷积核的初始化bias：{}\n".format( params[1]))
    print("全连接层的初始化参数：{}\n".format( params[2]))
    print("全连接层的初始化bias：{}\n".format( params[3]))

    print("卷积核的初始化参数的size：{}\n".format(params[0].size()))
    print("卷积核的初始化bias的size：{}\n".format( params[1].size()))
    print("全连接层的初始化参数的size：{}\n".format( params[2].size()))
    print("全连接层的初始化bias的size：{}\n".format( params[3].size()))

    input = Variable(torch.randn(1, 1, 5, 5))
    output = net(input)