import torch
from torch import nn
from torch.nn import functional as F
class ResBlk(nn.Module):
"""
resnet block
"""
def __init__(self, ch_in, ch_out):
"""
:param ch_in:
:param ch_out:
"""
super(ResBlk, self).__init__()
self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1)
self.bn1 = nn.BatchNorm2d(ch_out)
self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)
self.bn2 = nn.BatchNorm2d(ch_out)
self.extra = nn.Sequential()
if ch_out != ch_in:
# [b, ch_in, h, w] => [b, ch_out, h, w]
self.extra = nn.Sequential(
nn.Conv2d(ch_in, ch_out, kernel_size=1, stride=1),
nn.BatchNorm2d(ch_out)
)
def forward(self, x):
"""
:param x: [b, ch, h, w]
:return:
"""
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
# short cut.
# extra module: [b, ch_in, h, w] => [b, ch_out, h, w]
# element-wise add:
out = self.extra(x) + out
return out
class ResNet18(nn.Module):
def __init__(self):
super(ResNet18, self).__init__()
self.conv1 = nn.Sequential(
nn.Conv2d(3, 16, kernel_size=3, stride=3, padding=0),
nn.BatchNorm2d(16)
)
# followed 4 blocks
# [b, 64, h, w] => [b, 128, h ,w]
self.blk1 = ResBlk(16, 32)
# [b, 128, h, w] => [b, 256, h, w]
self.blk2 = ResBlk(32, 64)
# # [b, 256, h, w] => [b, 512, h, w]
self.blk3 = ResBlk(64, 128)
# # [b, 512, h, w] => [b, 1024, h, w]
self.blk4 = ResBlk(128, 256)
self.outlayer = nn.Linear(256*10*10, 10)
def forward(self, x):
"""
:param x:
:return:
"""
x = F.relu(self.conv1(x))
# [b, 64, h, w] => [b, 1024, h, w]
x = self.blk1(x)
x = self.blk2(x)
x = self.blk3(x)
x = self.blk4(x)
# print(x.shape)
x = x.view(x.size(0), -1)
x = self.outlayer(x)
return x
def main():
blk = ResBlk(64, 128)
tmp = torch.randn(2, 64,32, 32)
out = blk(tmp)
print('blkk', out.shape)
model = ResNet18()
tmp = torch.randn(2, 3, 32, 32)
out = model(tmp)
print('resnet:', out.shape)
if __name__ == '__main__':
main()
这是老师写的代码,自己的代码有点儿乱就不贴了
最大的感想就是CNN里有了stride和padding之后,[b, chn, h,w],太容易乱了 很容易出来的x和下一步接受的x对不上。
主要是会影响h,w
然后是cnn接fc要记得打平后面的 chn* H * W, 即
把cnn的 [b, chn ,h ,w] 打平成[b, chnhw]
有一个关键的short cut
错把
out = self.extra(x) + out
写成
out = self.extra(out) +x
花了有俩小时找这个问题,还是对网络中间的维度变换不够熟悉,
对short cut理解不好
from resnet_teacher import ResNet18
def main():
batchsz = 32
cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
]), download=True)
cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)
cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([
transforms.Resize((32, 32)),
transforms.ToTensor()
]), download=True)
cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)
x, label = iter(cifar_train).next()
print('x:', x.shape, 'label:', label.shape)
device = torch.device('cuda')
# model = Lenet5().to(device)
model = ResNet18()
criteon = nn.CrossEntropyLoss().to(device)
optimizer = optim.Adam(model.parameters(), lr=1e-3)
print(model)
for epoch in range(1000):
model.train()
for batchidx, (x, label) in enumerate(cifar_train):
# [b, 3, 32, 32]
# [b]
#x, label = x.to(device), label.to(device)
logits = model(x)
# logits: [b, 10]
# label: [b]
# loss: tensor scalar
loss = criteon(logits, label)
# backprop
optimizer.zero_grad()
loss.backward()
optimizer.step()
#
print(epoch, 'loss:', loss.item())
model.eval()
with torch.no_grad():
# test
total_correct = 0
total_num = 0
for x, label in cifar_test:
# [b, 3, 32, 32]
# [b]
#x, label = x.to(device), label.to(device)
# [b, 10]
logits = model(x)
# [b]
pred = logits.argmax(dim=1)
# [b] vs [b] => scalar tensor
correct = torch.eq(pred, label).float().sum().item()
total_correct += correct
total_num += x.size(0)
# print(correct)
acc = total_correct / total_num
print(epoch, 'acc:', acc)
if __name__ == '__main__':
main()