如何将 CNN LSTM 形式的 keras 转换为 pytorch

Question

我正在尝试将 keras 的 CNN LSTM 转换为 pytorch，但我遇到了问题。

ConvNN_model = models.Sequential()
ConvNN_model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 1)))
ConvNN_model.add(layers.MaxPooling2D((2, 2)))
ConvNN_model.add(layers.Conv2D(64, (3, 3), activation='relu'))
ConvNN_model.add(TimeDistributed(LSTM(128, activation='relu')))
ConvNN_model.add(Dropout(0.2))
ConvNN_model.add(LSTM(128, activation='relu'))
ConvNN_model.add(layers.Dense(64, activation='relu'))
ConvNN_model.add(layers.Dropout(0.25))
ConvNN_model.add(layers.Dense(15, activation='softmax'))

如何将上述代码从 Keras 转换到 Pytorch？

Answer 1

这是你在 Keras 中的 CNN：

ConvNN_model = models.Sequential()
ConvNN_model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(64, 64, 1)))
ConvNN_model.add(layers.MaxPooling2D((2, 2)))
ConvNN_model.add(layers.Conv2D(64, (3, 3), activation='relu'))
ConvNN_model.add(TimeDistributed(LSTM(128, activation='relu')))
ConvNN_model.add(Dropout(0.2))
ConvNN_model.add(LSTM(128, activation='relu'))
ConvNN_model.add(layers.Dense(64, activation='relu'))
ConvNN_model.add(layers.Dropout(0.25))
ConvNN_model.add(layers.Dense(15, activation='softmax'))

这是 PyTorch 中的等效代码：

class ConvNN_model(nn.Module):
    def __init__(self):
        super(ConvNN_model, self).__init__()
        self.layers = nn.Sequential(
                         nn.Conv2d(1, 32, kernel_size=3),
                         nn.ReLU(),
                         nn.MaxPool2d((2, 2)),
                         nn.Conv2d(32, 64, kernel_size=3),
                         nn.ReLU(),
                         TimeDistributed(nn.LSTM(128, 128)),
                         nn.Dropout(0.2),
                         nn.LSTM(128, 128),
                         nn.ReLU(),
                         nn.Linear(128, 64),
                         nn.ReLU(),
                         nn.Dropout(0.25),
                         nn.Linear(64, 15),
                         nn.Softmax()
                         )
    def forward(self, x):
        return self.layers(x)

请记住，PyTorch 中没有 TimeDistributed class 的等效模块，因此您必须自己构建它。这是您可以使用的（来自 here）：

class TimeDistributed(nn.Module):
    def __init__(self, module, batch_first=False):
        super(TimeDistributed, self).__init__()
        self.module = module
        self.batch_first = batch_first

    def forward(self, x):

        if len(x.size()) <= 2:
            return self.module(x)

        # Squash samples and timesteps into a single axis
        x_reshape = x.contiguous().view(-1, x.size(-1))  # (samples * timesteps, input_size)

        y = self.module(x_reshape)

        # We have to reshape Y
        if self.batch_first:
            y = y.contiguous().view(x.size(0), -1, y.size(-1))  # (samples, timesteps, output_size)
        else:
            y = y.view(-1, x.size(1), y.size(-1))  # (timesteps, samples, output_size)

        return y

剥猫皮的方法有百万零一种；您不必像我一样在 nn.Sequential 块中创建整个网络。或者，如果您想坚持使用顺序方法以与 Keras 保持一致，则不需要 subclass nn.Module 并完全使用顺序层。

如何将 CNN LSTM 形式的 keras 转换为 pytorch

How to convert a CNN LSTM form keras to pytorch

conv-neural-network

lstm

keras

pytorch