def resnet_block(in_channels, out_channels, num_residuals, first_block=False):
if first_block:
assert in_channels == out_channels # 第一个模块的通道数同输入通道数一致
blk = []
for i in range(num_residuals):
if i == 0 and not first_block:
blk.append(Residual(in_channels, out_channels, use_1x1conv=True, stride=2))
else:
blk.append(Residual(out_channels, out_channels))
return nn.Sequential(*blk)
net.add_module("resnet_block1", resnet_block(64, 64, 2, first_block=True))
net.add_module("resnet_block2", resnet_block(64, 128, 2))
net.add_module("resnet_block3", resnet_block(128, 256, 2))
net.add_module("resnet_block4", resnet_block(256, 512, 2))
net.add_module("global_avg_pool", d2l.GlobalAvgPool2d()) # GlobalAvgPool2d的输出: (Batch, 512, 1, 1)
net.add_module("fc", nn.Sequential(d2l.FlattenLayer(), nn.Linear(512, 10)))
X = torch.rand((1, 1, 224, 224))
for name, layer in net.named_children():
X = layer(X)
print(name, ' output shape:\t', X.shape)
0 output shape: torch.Size([1, 64, 112, 112])
1 output shape: torch.Size([1, 64, 112, 112])
2 output shape: torch.Size([1, 64, 112, 112])
3 output shape: torch.Size([1, 64, 56, 56])
resnet_block1 output shape: torch.Size([1, 64, 56, 56])
resnet_block2 output shape: torch.Size([1, 128, 28, 28])
resnet_block3 output shape: torch.Size([1, 256, 14, 14])
resnet_block4 output shape: torch.Size([1, 512, 7, 7])
global_avg_pool output shape: torch.Size([1, 512, 1, 1])
fc output shape: torch.Size([1, 10])
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
Inception(256, 128, (128, 192), (32, 96), 64),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
Inception(512, 160, (112, 224), (24, 64), 64),
Inception(512, 128, (128, 256), (24, 64), 64),
Inception(512, 112, (144, 288), (32, 64), 64),
Inception(528, 256, (160, 320), (32, 128), 128),
nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
Inception(832, 384, (192, 384), (48, 128), 128),
d2l.GlobalAvgPool2d())
net = nn.Sequential(b1, b2, b3, b4, b5, d2l.FlattenLayer(),
nn.Linear(1024, 10))
net = nn.Sequential(b1, b2, b3, b4, b5, d2l.FlattenLayer(),
nn.Linear(1024, 10))
X = torch.rand(1, 1, 96, 96)
for blk in net.children():
X = blk(X)
print('output shape: ', X.shape)
#batchsize=128
batch_size = 16
for i, num_convs in enumerate(num_convs_in_dense_blocks):
DB = DenseBlock(num_convs, num_channels, growth_rate)
net.add_module("DenseBlosk_%d" % i, DB)
# 上一个稠密块的输出通道数
num_channels = DB.out_channels
# 在稠密块之间加入通道数减半的过渡层
if i != len(num_convs_in_dense_blocks) - 1:
net.add_module("transition_block_%d" % i,
transition_block(num_channels, num_channels // 2))
num_channels = num_channels // 2
net.add_module("BN", nn.BatchNorm2d(num_channels))
net.add_module("relu", nn.ReLU())
net.add_module(
"global_avg_pool",
d2l.GlobalAvgPool2d()) # GlobalAvgPool2d的输出: (Batch, num_channels, 1, 1)
net.add_module("fc",
nn.Sequential(d2l.FlattenLayer(), nn.Linear(num_channels, 10)))
#依据计算能力选择
batch_size = 0
#batch_size = 256
batch_size = 16
assert batch_size > 0, '未选择batch_size'
#读取数据，使用其他数据集时更改该部分
def load_data_fashion_mnist(batch_size,
resize=None,
root='/home/kesci/input/FashionMNIST2065'):
"""Download the fashion mnist dataset and then load into memory."""