打赏

VGG使用块的网络——pytorch版

import torch
from torch import nn
from d2l import torch as d2l

def vgg_block(num_convs,in_channels,out_channels):
    layers = []
    for _ in range(num_convs):
        layers.append(nn.Conv2d(
            in_channels,out_channels,kernel_size=3, padding=1
        ))
        layers.append(nn.ReLU())
        # 每个输出保证都是一样的
        in_channels = out_channels
    layers.append(nn.MaxPool2d(
        kernel_size=2,stride=2
    ))
    return nn.Sequential(*layers)

conv_arch=((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))

def vgg(conv_arch):
    conv_blks=[]
    in_channels=1
    for (num_convs,out_channels) in conv_arch:
        conv_blks.append(vgg_block(
            num_convs,in_channels,out_channels
        ))
        in_channels=out_channels
    return nn.Sequential(
        *conv_blks,nn.Flatten(),
        nn.Linear(out_channels*7*7,4096),nn.ReLU(),
        nn.Dropout(0.5),nn.Linear(4096,4096),nn.ReLU(),
        nn.Dropout(0.5),nn.Linear(4096,10)
    )

net = vgg(conv_arch)

x = torch.randn(size=(1,1,224,224))
for blk in net:
    x = blk(x)
    print(blk.__class__.__name__,'output shape:\t',x.shape)

ratio = 4
small_conv_arch=[(pair[0],pair[1]//ratio) for pair in conv_arch]
net = vgg(small_conv_arch)

lr, num_epochs, batch_size = 0.05, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())

 

posted @ 2023-08-06 14:44  不像话  阅读(13)  评论(0编辑  收藏  举报