我正在尝试在MNIST上的TensorFlow中构建卷积自动编码器.如何以与原始形状相同的形状获得解码图像

Question

我已经使用图层API编写了编码器和解码器函数。两者都深3层。

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也具有padding参数。将其设置为same，因为卷积应该解决此问题。否面

请注意，您还需要您的最后一个卷积转置层才能使用1个过滤器 - 现在，您的重建是[？，28，28，32]，但是您需要[？，28，28，1]输入。