nn.MaxPool2d(2, 2),
FlattenLayer(),
nn.Linear(16 * 4 * 4, 120),
nn.BatchNorm1d(120),
nn.Sigmoid(),
nn.Linear(120, 84),
nn.BatchNorm1d(84),
nn.Sigmoid(),
nn.Linear(84, 10))
if __name__ == '__main__':
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
net = LeNet()
print(net)
batch_size = 256
train_iter, test_iter = fashion_mnist.load_data_fashion_mnist(
batch_size=batch_size)
lr = 0.001
num_epochs = 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
trainer.train(net, train_iter, test_iter, batch_size, optimizer, device,
num_epochs)
print("-" * 42)
print(lenet_bn)
optimizer = torch.optim.Adam(lenet_bn.parameters(), lr=lr)
train_iter, test_iter = fashion_mnist.load_data_fashion_mnist(
batch_size=batch_size)
trainer.train(lenet_bn, train_iter, test_iter, batch_size, optimizer,
device, num_epochs)
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, 3, 1, 1),
nn.MaxPool2d(3, 2),
nn.Dropout(0.5),
# 标签类别数是10
nin_block(384, 10, 3, 1, 1),
GlobalAvgPool2d(),
FlattenLayer()
)
if __name__ == '__main__':
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(net)
X = torch.rand(1, 1, 224, 224)
for name, blk in net.named_children():
X = blk(X)
print(name, 'output shape:', X.shape)
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 = fashion_mnist.load_data_fashion_mnist(batch_size, resize=224)
lr, num_epochs = 0.001, 5
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
trainer.train(net, train_iter, test_iter, batch_size, optimizer, device, num_epochs)