0

I am creating a convolution autoencoder in tensorflow. I got this exact error:

tensorflow.python.framework.errors.InvalidArgumentError: Conv2DBackpropInput: Number of rows of out_backprop doesn't match computed: actual = 8, computed = 12
     [[Node: conv2d_transpose = Conv2DBackpropInput[T=DT_FLOAT, data_format="NHWC", padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/cpu:0"](conv2d_transpose/output_shape, Variable_1/read, MaxPool_1)]]

Relevant code:

l1d = tf.nn.relu(tf.nn.conv2d_transpose(l1da, w2, [10, 12, 12, 32], strides=[1, 1, 1, 1], padding='SAME'))

where 

w2 = tf.Variable(tf.random_normal([5, 5, 32, 64], stddev=0.01))

I checked the shape of the input to conv2d_transpose i.e. l1da and it is correct(10x8x8x64). The batch size is 10, input to this layer is in the form of 8x8x64, and the output is supposed to be 12x12x32.

What am I missing?

David Parks
  • 30,789
  • 47
  • 185
  • 328
goluhaque
  • 561
  • 5
  • 17

1 Answers1

4

Found the error. Padding should be "Valid", not "Same".

goluhaque
  • 561
  • 5
  • 17
  • Exact same question answered in detail here: http://stackoverflow.com/questions/35488717/confused-about-conv2d-transpose?noredirect=1&lq=1 – anh_ng8 Sep 23 '16 at 12:19