Pytorch深度学习(3) -- CNN及其进阶模型实现
1.LeNet
1.1 模型图
1.2 模型实现
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')
class LeNet(nn.Module):
def __init__(self):
super(LeNet, self).__init__()
self.conv = nn.Sequential(
nn.Conv2d(1, 6, 5), # in_channels, out_channels, kernel_size
nn.Sigmoid(),
nn.MaxPool2d(2, 2), # kernel_size, stride
nn.Conv2d(6, 16, 5),
nn.Sigmoid(),
nn.MaxPool2d(2, 2)
)
self.fc = nn.Sequential(
nn.Linear(16*4*4, 120),
nn.Sigmoid(),
nn.Linear(120, 84),
nn.Sigmoid(),
nn.Linear(84, 10)
)
def forward(self, img):
feature = self.conv(img)
output = self.fc(feature.view(img.shape[0], -1))
return output
接下来查看每个层的形状。
net = LeNet()
print(net)
输出:
LeNet(
(conv): Sequential(
(0): Conv2d(1, 6, kernel_size=(5, 5), stride=(1, 1))
(1): Sigmoid()
(2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(3): Conv2d(6, 16, kernel_size=(5, 5), stride=(1, 1))
(4): Sigmoid()
(5): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(fc): Sequential(
(0): Linear(in_features=256, out_features=120, bias=True)
(1): Sigmoid()
(2): Linear(in_features=120, out_features=84, bias=True)
(3): Sigmoid()
(4): Linear(in_features=84, out_features=10, bias=True)
)
)
1.3 计算准确率函数(下同,不赘述)
# 本函数已保存在d2lzh_pytorch包中方便以后使用。该函数将被逐步改进。
def evaluate_accuracy(data_iter, net, device=None):
if device is None and isinstance(net, torch.nn.Module):
# 如果没指定device就使用net的device
device = list(net.parameters())[0].device
acc_sum, n = 0.0, 0
with torch.no_grad():
for X, y in data_iter:
if isinstance(net, torch.nn.Module):
net.eval() # 评估模式, 这会关闭dropout
acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item()
net.train() # 改回训练模式
else: # 自定义的模型, 3.13节之后不会用到, 不考虑GPU
if('is_training' in net.__code__.co_varnames): # 如果有is_training这个参数
# 将is_training设置成False
acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item()
else:
acc_sum += (net(X).argmax(dim=1) == y).float().sum().item()
n += y.shape[0]
return acc_sum / n