如何避免卷积神经网络中的零填充

Question

我有一个卷积神经网络，它在我的数据集上比其他网络做得更好。问题在于ZeroPadding2D 我需要放置以说明向下/向上采样；它在输出中创建工件（零样本）。那么，如何在不改变网络结构（层）的情况下避免ZeroPadding2D 选项。我需要保持结构原样（no.layers）并且可能会改变 1-过滤器 2-内核 3- 我的数据中的第一个维度（例如 96） 4-任何其他选项 贝娄是我的 CNN

input_img = Input(shape=(96, 44, 1), name='full')  

x = GaussianNoise(.1)(input_img)
x = Conv2D(64, (5, 5), activation='relu', padding='same')(x)
x = AveragePooling2D((2, 2), padding='same')(x)
x = Dropout(0.1)(x)
x = Conv2D(128, (5, 5), activation='relu', padding='same')(x)
x = AveragePooling2D((2, 2), padding='same')(x)
x = Dropout(0.2)(x)
x = Conv2D(512, (5, 5), activation='relu', padding='same')(x)
encoded = AveragePooling2D((2, 2), padding='same')(x)
x = Dropout(0.2)(x)

# at this point the representation is (4, 4, 8) i.e. 128-dimensional
x = Conv2D(512, (5, 5), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Dropout(0.2)(x)
x = Conv2D(128, (5, 5), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Dropout(0.12)(x)
x = Conv2D(64, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
x = Dropout(0.12)(x)
x = ZeroPadding2D(((4, 0), (0, 0)))(x)
decoded = Conv2D(1, (5, 5), activation='tanh', padding='same',
                 name='out')(x)

autoencoder = Model(input_img, decoded)

Answer 1

我想如果您将 Upsampling+ ZeroPadding 部分替换为 Conv2DTranspose ，这可能有助于解决您的问题。

看看这里：

https://www.tensorflow.org/api_docs/python/tf/keras/layers/Conv2DTranspose