是否有使用 MxNet 构建卷积自动编码器的玩具示例？

Question

我正在寻找使用 MxNet 的卷积自动编码器的实现。但是基于Fully Connected Networks的autoencoder只有一个例子，就是here。在 github 中也有一个 issue 提出类似的问题，但收到的回复很少。是否有使用 MxNet 实现的卷积自动编码器的玩具示例？

Answer 1

mxnet 中仍然没有卷积自动编码器示例，尽管有一些 progress in research in that area. Anyway, there is a ticket for that in MxNet github, but it is still open. You are more than welcome to contribute, by, for example, migrating the code from Keras。

Answer 2

请在 Mxnet Gluon 中找到 Conv Autoencoder 模型的示例。代码引用自 here。在 Gluon 中以标准方式训练此模型。

from mxnet import gluon as g

class CNNAutoencoder(g.nn.HybridBlock):
    def __init__(self):
        super(CNNAutoencoder, self).__init__()
        with self.name_scope():
            self.encoder = g.nn.HybridSequential('encoder_')
            with self.encoder.name_scope():
                self.encoder.add(g.nn.Conv2D(16, 3, strides=3, padding=1, activation='relu'))
                self.encoder.add(g.nn.MaxPool2D(2, 2))
                self.encoder.add(g.nn.Conv2D(8, 3, strides=2, padding=1, activation='relu'))
                self.encoder.add(g.nn.MaxPool2D(2, 1))

            self.decoder = g.nn.HybridSequential('decoder_')
            with self.decoder.name_scope():
                self.decoder.add(g.nn.Conv2DTranspose(16, 3, strides=2, activation='relu'))
                self.decoder.add(g.nn.Conv2DTranspose(8, 5, strides=3, padding=1, activation='relu'))
                self.decoder.add(g.nn.Conv2DTranspose(1, 2, strides=2, padding=1, activation='tanh'))

    def forward(self, x):
        x = self.encoder(x)
        x = self.decoder(x)
        return x

model = CNNAutoencoder()
model.hybridize()

是否有使用 MxNet 构建卷积自动编码器的玩具示例？

Is there any toy example of building convolutional autoencoders using MxNet?

machine-learning

convolution

computer-vision

autoencoder

mxnet