nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b2 = nn.Sequential(*resnet_block(64, 256,
3)) # can't get first_block figured out
b3 = nn.Sequential(*resnet_block(256, 512, 4))
b4 = nn.Sequential(*resnet_block(512, 1024, 6))
b5 = nn.Sequential(*resnet_block(1024, 2048, 3))
# ./resnet18.svg.png
net = nn.Sequential(b1, b2, b3, b4, b5, nn.AdaptiveAvgPool2d((1, 1)),
nn.Flatten(), nn.Linear(2048, 10))
# Examine the net
X = torch.rand(size=(1, 1, 224, 224))
for layer in net:
X = layer(X)
print(layer.__class__.__name__, 'output shape:\t', X.shape)
# RUN
lr, num_epochs, batch_size = 0.05, 10, 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr)
# loss 0.152, train acc 0.943, test acc 0.852
# 642.2 examples/sec on cuda:0
# Resnet50 Conclusions:
# test acc about the same as resnet18.
# train acc ~10 points higher
# loss much lower
def forward(self, X):
# If `X` is not on the main memory, copy `moving_mean` and
# `moving_var` to the device where `X` is located
if self.moving_mean.device != X.device:
self.moving_mean = self.moving_mean.to(X.device)
self.moving_var = self.moving_var.to(X.device)
# Save the updated `moving_mean` and `moving_var`
Y, self.moving_mean, self.moving_var = batch_norm(
X, self.gamma, self.beta, self.moving_mean, self.moving_var,
eps=1e-5, momentum=0.9)
return Y
net = nn.Sequential(nn.Conv2d(1, 6, kernel_size=5), BatchNorm(6, num_dims=4),
nn.Sigmoid(), nn.AvgPool2d(kernel_size=2, stride=2),
nn.Conv2d(6, 16,
kernel_size=5), BatchNorm(16, num_dims=4),
nn.Sigmoid(), nn.AvgPool2d(kernel_size=2, stride=2),
nn.Flatten(), nn.Linear(16 * 4 * 4, 120),
BatchNorm(120, num_dims=2), nn.Sigmoid(),
nn.Linear(120, 84), BatchNorm(84, num_dims=2),
nn.Sigmoid(), nn.Linear(84, 10))
lr, num_epochs, batch_size = 1.0, 10, 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())