Question

我使用图层API编写了编码器和解码器功能。两者都是3层深。

def Enocder(real_img):
    with tf.variable_scope("encoder"):
        conv1 = tf.layers.conv2d(inputs=X, filters=32, kernel_size=[
                                 5, 5], use_bias=True, padding="same", activation=tf.nn.leaky_relu)
        pool1 = tf.layers.max_pooling2d(
            inputs=conv1, pool_size=[2, 2], padding="same", strides=[2, 2])
        conv2 = tf.layers.conv2d(inputs=pool1,  filters=64, kernel_size=[
                                 5, 5], use_bias=True, padding="same", activation=tf.nn.leaky_relu)
        pool2 = tf.layers.max_pooling2d(
            inputs=conv2, pool_size=[2, 2],  padding="same",strides=[2, 2])
        conv3 = tf.layers.conv2d(inputs=pool2, filters=128, kernel_size=[
                                 5, 5], use_bias=True, padding="same", activation=tf.nn.leaky_relu)
        pool3 = tf.layers.max_pooling2d(
            inputs=conv3, pool_size=[2, 2], padding="same", strides=[2, 2])
        return pool3


def Decoder(Z):
    with tf.variable_scope("decoder"):
        deconv1 = tf.layers.conv2d_transpose(inputs=Z, filters=128, kernel_size=[
                                             5, 5], padding="same", strides=[2, 2])
        deconv2 = tf.layers.conv2d_transpose(inputs=deconv1, filters=64, kernel_size=[
                                             5, 5], padding="same", strides=[2, 2])
        deconv3 = tf.layers.conv2d_transpose(inputs=deconv2, filters=32, kernel_size=[
                                             5, 5], padding="same", strides=[2, 2])
        deconv4 = tf.layers.conv2d_transpose(inputs=deconv3, filters=1, kernel_size=[5,5], padding="same", strides=[2,2])

        return deconv4

real_img = tf.placeholder(dtype=tf.float32, shape=[None, 784])
X = tf.reshape(real_img, [-1, 28, 28, 1])
enc = Enocder(X)
dec = Decoder(enc)
cost = tf.reduce_sum(tf.square(X - dec))

错误：

    ValueError: Dimensions must be equal, but are 28 and 24 for 'sub' (op: 'Sub') with input shapes: [?,28,28,1], [?,64,64,1].

如何获得28x28形状的解码图像？

Answer 1

tf.layers.max_pooling2d也有一个padding参数。对于卷积，将其设置为same应解决此问题。否则，您的池将略微缩小输入（超出大步），如此处所示。

请注意，你还需要你的最后一个卷积转置图层才能使用1个滤镜 - 现在你的重建将是[？，28,28,32]，但你需要[？，28,28,1]像输入

我正在尝试在MNIST上的tensorflow中构建一个卷积自动编码器。如何使解码图像与原始图像的形状相同？

1 个答案: