torch之NIN

酥酥 发布于 2022-04-17 90 次阅读

网络中的网络（NiN）

				
					import time
import torch
from torch import nn, optim

import sys
sys.path.append("..") 
import d2lzh_pytorch as d2l
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

print(torch.__version__)
print(device)
				
			
				
					def nin_block(in_channels, out_channels, kernel_size, stride, padding):
    blk = nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU(),
                        nn.Conv2d(out_channels, out_channels, kernel_size=1),
                        nn.ReLU())
    return blk

NiN模型

				
					net = nn.Sequential(
    nin_block(1, 96, kernel_size=11, stride=4, padding=0),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(96, 256, kernel_size=5, stride=1, padding=2),
    nn.MaxPool2d(kernel_size=3, stride=2),
    nin_block(256, 384, kernel_size=3, stride=1, padding=1),
    nn.MaxPool2d(kernel_size=3, stride=2), 
    nn.Dropout(0.5),
    # 标签类别数是10
    nin_block(384, 10, kernel_size=3, stride=1, padding=1),
    # 全局平均池化层可通过将窗口形状设置成输入的高和宽实现
    nn.AvgPool2d(kernel_size=5),
    # 将四维的输出转成二维的输出，其形状为(批量大小, 10)
    d2l.FlattenLayer())
				
			
				
					X = torch.rand(1, 1, 224, 224)

for name, blk in net.named_children(): 
    X = blk(X)
    print(name, 'output shape: ', X.shape)
				
			
0 output shape:  torch.Size([1, 96, 54, 54])
1 output shape:  torch.Size([1, 96, 26, 26])
2 output shape:  torch.Size([1, 256, 26, 26])
3 output shape:  torch.Size([1, 256, 12, 12])
4 output shape:  torch.Size([1, 384, 12, 12])
5 output shape:  torch.Size([1, 384, 5, 5])
6 output shape:  torch.Size([1, 384, 5, 5])
7 output shape:  torch.Size([1, 10, 5, 5])
8 output shape:  torch.Size([1, 10, 1, 1])
9 output shape:  torch.Size([1, 10])

获取数据和训练模型

				
					batch_size = 128
# 如出现“out of memory”的报错信息，可减小batch_size或resize
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.002, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
d2l.train_ch5(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)
				
			
training on  cuda
epoch 1, loss 0.0101, train acc 0.513, test acc 0.734, time 260.9 sec
epoch 2, loss 0.0050, train acc 0.763, test acc 0.754, time 175.1 sec
epoch 3, loss 0.0041, train acc 0.808, test acc 0.826, time 151.0 sec
epoch 4, loss 0.0037, train acc 0.828, test acc 0.827, time 151.0 sec
epoch 5, loss 0.0034, train acc 0.839, test acc 0.831, time 151.0 sec