“ Encoder / conv6 / Conv2D”的2减去3导致的负尺寸大小

Question

我正在尝试在Tensorflow中实现自动编码器。 我是Python和StackOverflow的初学者。 这两个是我的编码器和解码器，我的train_data.shape是（42000,28,28,1）（mnist数据集）。

def Network(Input):
with tf.name_scope("Encoder"):
    #encoder starts here
    conv1 = tf.layers.conv2d(Input, filters = 64, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv1')
    conv2 = tf.layers.conv2d(conv1, filters = 64, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv2')
    pool1 = tf.layers.max_pooling2d(conv2, pool_size = 2, strides = 2, name = 'pool1')

    conv3 = tf.layers.conv2d(pool1, filters = 128, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv3')
    conv4 = tf.layers.conv2d(conv3, filters = 128, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv4')
    pool2 = tf.layers.max_pooling2d(conv4, pool_size = 2, strides = 2, name = 'pool2')


    conv5 = tf.layers.conv2d(pool2, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv5')
    conv6 = tf.layers.conv2d(conv5, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv6')
    conv7 = tf.layers.conv2d(conv6, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv7')
    pool3 = tf.layers.max_pooling2d(conv7, pool_size = 2, strides = 2, name = 'pool3')

    conv8 = tf.layers.conv2d(pool3, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv8')
    conv9 = tf.layers.conv2d(conv8, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv9')
    conv10 = tf.layers.conv2d(conv9, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv10')
    pool4 = tf.layers.max_pooling2d(conv10, pool_size = 2, strides = 2, name = 'pool4')

    conv11 = tf.layers.conv2d(pool4, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv11')
    conv12 = tf.layers.conv2d(conv11, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv12')
    conv13 = tf.layers.conv2d(conv12, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'conv13')

    pool5 = tf.layers.max_pooling2d(conv13, pool_size = 2, strides = 2, name = 'pool5')

return pool5

..

def Decoder(pool5):
with tf.name_scope("Decoder"):

    deconv1=tf.layers.conv2d_transpose(pool5, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv1')
    deconv2=tf.layers.conv2d_transpose(deconv1, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv2')
    deconv3=tf.layers.conv2d_transpose(deconv2, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv3')

    pool6=tf.layers.max_pooling2d(deconv3, pool_size = 2, strides = 2, name = 'pool6')
    deconv4 = tf.layers.conv2d_transpose(pool6, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv4')
    deconv5 = tf.layers.conv2d_transpose(deconv4, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv5')
    deconv6 = tf.layers.conv2d_transpose(deconv5, filters = 512, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv6')

    pool7 = tf.layers.max_pooling2d(deconv6, pool_size = 2, strides = 2, name = 'pool7')
    deconv7 = tf.layers.conv2d_transpose(pool7, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv7')
    deconv8 = tf.layers.conv2d_transpose(deconv7, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv8')
    deconv9 = tf.layers.conv2d_transpose(deconv8, filters = 256, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv9')

    pool8 = tf.layers.max_pooling2d(deconv9, pool_size = 2, strides = 2, name = 'pool8')
    deconv10 = tf.layers.conv2d_transpose(pool8, filters = 128, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv10')
    deconv11 = tf.layers.conv2d_transpose(deconv10, filters = 128, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv11')

    pool9= tf.layers.max_pooling2d(deconv11, pool_size = 2, strides = 2, name = 'pool9')
    deconv12 = tf.layers.conv2d_transpose(pool9, filters = 64, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv12')
    deconv13 = tf.layers.conv2d_transpose(deconv12, filters = 64, kernel_size = 3, strides = 1, activation = tf.nn.relu, name = 'deconv13')


    flat = tf.contrib.layers.flatten(deconv13)
    fc1 = tf.layers.dense(flat, units = 1024, activation = tf.nn.relu, name = 'fc1')
    fc2 = tf.layers.dense(fc1, units = 10, activation = None, name = 'fc2')

return fc2

我遇到这个错误：

 ----------------------------------------------------------------------
 ValueError                                Traceback (most recent call    last)


ValueError: Negative dimension size caused by subtracting 3 from 2 for 'Encoder/conv6/Conv2D' (op: 'Conv2D') with input shapes: [?,2,2,256],                   [3,3,256,256].

我感觉输入中有一些错误，请提出每次conv2d操作后如何可视化张量的形状。

Input = tf.placeholder(dtype = tf.float32, shape = [None, 28, 28, 1])

Answer 1

要可视化张量t的形状，请使用t.get_shape() 。 该错误明确表明您正在尝试在太小的输入上使用太大的内核。 从斯坦福大学的CS231n类笔记中，您可以得到方程式，以在给定特定内核大小，步幅和填充的情况下计算数据的确切形状 您应该减小内核大小，增加步幅或获得更大的输入以执行许多卷积。 请记住， max_pooling还将收缩输入，其大小是该层中池大小的多少倍，因此，如果为2，则数据将收缩2倍。