Question

我在理解ResNet架构的以下代码部分时遇到了问题。完整代码位于https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/02-intermediate/deep_residual_network/main-gpu.py。我对Python不太熟悉。

# Residual Block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

# ResNet Module
class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block, 16, layers[0])
        self.layer2 = self.make_layer(block, 32, layers[0], 2)
        self.layer3 = self.make_layer(block, 64, layers[1], 2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(block(self.in_channels, out_channels, stride, downsample))
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

resnet = ResNet(ResidualBlock, [3, 3, 3])

我的主要问题是为什么我们应该通过＆＃39;阻止＆＃39;每次？在函数

中

def make_layer(self, block, out_channels, blocks, stride=1):

而不是传递＆＃39;阻止＆＃39;为什么我们不能创建一个＆＃39; ResidualBlock＆＃39;并按如下方式添加图层？

   block = ResidualBlock(self.in_channels, out_channels, stride, downsample)
   layers.append(block)

Answer 1

ResNet模块设计为通用模块，因此可以创建具有任意块的网络。因此，如果您未传递要创建的block，则必须明确写下该块的名称，如下所示。

# Residual Block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.conv2(out)
        out = self.bn2(out)
        if self.downsample:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

# ResNet Module
class ResNet(nn.Module):
    def __init__(self, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(16, layers[0])
        self.layer2 = self.make_layer(32, layers[0], 2)
        self.layer3 = self.make_layer(64, layers[1], 2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)

    def make_layer(self, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels))
        layers = []
        layers.append(ResidualBlock(self.in_channels, out_channels, stride, downsample))   # Major change here
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(ResidualBlock(out_channels, out_channels))    # Major change here
        return nn.Sequential(*layers)

    def forward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

resnet = ResNet([3, 3, 3])

这会降低ResNet模块的功能，并仅将其与ResidualBlock绑定。现在，如果您创建其他类型的块（比如ResidualBlock2），则需要专门为此创建另一个Resnet2模块。因此，最好创建一个接收ResNet参数的通用block模块，以便它可以与不同类型的块一起使用。

一个简单的python示例来澄清

假设您要创建一个可以对列表应用数学运算并返回其输出的函数。所以，您可以创建类似下面的内容

def exp(inp_list):
    out_list = []
    for num in inp_list:
        out_list.append(math.exp(num))
    return out_list

def floor(inp_list):
    out_list = []
    for num in inp_list:
        out_list.append(math.floor(num))
    return out_list

在这里，我们在一些输入列表上进行指数和底层操作。但是，我们可以通过定义一个与

相同的泛型函数来做得更好

def apply_func(fn, inp_list):
    out_list = []
    for num in inp_list:
        out_list.append(fn(num))
    return out_list

现在将此apply_func称为apply_func(math.exp, inp_list)表示指数，将apply_func(math.floor, inp_list)表示为楼层函数。这也为任何操作提供了可能性。

注意：这不是一个实际的例子，因为您始终可以使用map或list comprehension来实现相同的目标。但是，它清楚地证明了它的用途。

理解pyTorch中的代码

1 个答案:

一个简单的python示例来澄清