import torch
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l


class Residual(nn.Module):  
  def __init__(self, input_channels, num_channels,
              use_1x1conv=False, strides=1):
    super().__init__()
    self.conv1 = nn.Conv2d(input_channels, num_channels,
                kernel_size=3, padding=1, stride=strides)
    self.conv2 = nn.Conv2d(num_channels, num_channels,
                kernel_size=3, padding=1)
    if use_1x1conv: # 使用这个会把 input 的通道数改成和 ouput 一样
      self.conv3 = nn.Conv2d(input_channels, num_channels,
                     kernel_size=1, stride=strides)
    else:
      self.conv3 = None
      self.bn1 = nn.BatchNorm2d(num_channels)
      self.bn2 = nn.BatchNorm2d(num_channels)
      self.relu = nn.ReLU(inplace=True)

  def forward(self, X):
    Y = F.relu(self.bn1(self.conv1(X)))
    Y = self.bn2(self.conv2(Y))
    if self.conv3:
      X = self.conv3(X)
    Y += X
    return F.relu(Y)

# 输入和输出形状一致
blk = Residual(3,3)
X = torch.rand(4, 3, 6, 6)
Y = blk(X)
Y.shape

# 输出 torch.Size([4, 3, 6, 6])

# 增加通道数的同时，减半输出的高和宽
blk = Residual(3,6, use_1x1conv=True, strides=2)
blk(X).shape
# 输出 torch.Size([4, 6, 3, 3])

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
            nn.BatchNorm2d(64), nn.ReLU(),
            nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

def resnet_block(input_channels, num_channels, num_residuals,
          first_block=False):
  blk = []
  for i in range(num_residuals):
    if i == 0 and not first_block:
      blk.append(Residual(input_channels, num_channels,
                use_1x1conv=True, strides=2))
    else:
      blk.append(Residual(num_channels, num_channels))
  return blk

b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))

# 在 ResNet 中加入全局平均池化层，以及全连接层输出
net = nn.Sequential(b1, b2, b3, b4, b5,
          nn.AdaptiveAvgPool2d((1,1)),
          nn.Flatten(), nn.Linear(512, 10))

# 训练模型
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, d2l.try_gpu())