keras: Undefined output shape in Conv2DTranspose

If we use keras with tensorflow, the output shape of a Conv2DTranspose is undefined even if the input shape is fixed. This problem doesn’t happen with Conv2D . This is probably due to a bug in the implementation of Conv2DTranspose.

import tensorflow as tf

config = tf.ConfigProto()
config.gpu_options.allow_growth=True
sess = tf.Session(config=config)

from keras.layers.convolutional import Conv2DTranspose , Conv2D

layer1 = Conv2DTranspose( 8  , (4 , 4) , strides=(1, 1)  , data_format='channels_first'  , input_shape=(3,64,64) )
layer2 = Conv2D( 8 , (4, 4) , strides=(1, 1), input_shape=(3, 64, 64) , data_format='channels_first'  )

BATCH_SIZE = 32
x = tf.placeholder(tf.float32, shape=( BATCH_SIZE , 3, 64 , 64 ))
          
o1 = layer1( x )
o2 = layer2( x )


print o1.get_shape() # Prints (?, 8, ?, ?) , why???
print o2.get_shape() # Prints (32, 8, 61, 61) , which is correct

About this issue

Original URL
State: closed
Created 7 years ago
Reactions: 5
Comments: 21 (2 by maintainers)

Most upvoted comments

I can check the output shape with _keras_shape property of the layer.

+12

gdubrg on Nov 18, 2017

A nasty workaround is to explicitly mention the output shape.
<your_tensor>.set_shape(<output_shape>)

AnudeepKonda on Nov 18, 2017

Changing the imports to the Keras version included in Tensorflow also fixed the problem:

from tensorflow.python import keras
from tensorflow.python.keras.layers import Input, Conv2D, Conv2DTranspose
from tensorflow.python.keras import backend as K

assert K.image_data_format() == 'channels_last'

inp = Input(shape=(((32, 32, 3))))
out_1 = Conv2D(8, (3, 3), strides=(1, 1), padding='same')(inp)
out_2 = Conv2DTranspose(8, (3, 3), strides=(1, 1), padding='same')(inp)

print(out_1.shape)
print(out_2.shape)

(?, 32, 32, 8)
(?, 32, 32, 8)

Dobiasd on Mar 6, 2018

@wt-huang Is this really resolved? It seems like the solution above is “abandon Keras and use tf.keras”, which isn’t ideal.

kwaegel on Jul 26, 2019

My latest pull request fixes this issue: #13778

davideboschetto on Feb 15, 2020

@wt-huang This isn’t solved! Keras from TF and vanilla keras is not compatible. A project should use either tf.keras or just keras and not both. Changing the whole project to use tf.keras is a huge job.

quartzsaber on Sep 24, 2019

I too encoutered this bug.

The following code

from keras.models import Model
from keras.layers import Input, Conv2D, Conv2DTranspose
from keras import backend as K

assert K.image_data_format() == 'channels_last'

inp = Input(shape=(((32, 32, 3))))
out_1 = Conv2D(8, (3, 3), strides=(1, 1), padding='same')(inp)
out_2 = Conv2DTranspose(8, (3, 3), strides=(1, 1), padding='same')(inp)

print(out_1.shape)
print(out_2.shape)

produces this output (Keras Version 2.0.8, TensorFlow 1.3.0)

(?, 32, 32, 8)
(?, ?, ?, 8)

To me it looks like it is caused by this TensorFlow issue.

Dobiasd on Oct 17, 2017

I suppose that’s that, then. Still pretty annoying since, a) TF 2.0 is still in beta, and b) tf.keras is not a drop-in replacement, as evidenced by the week or so of work I had to put in switching over to get around this bug.

(The latter point may now be true with the 2.3.0 update, but I think that also points towards the high volatility in machine learning libraries.)

kwaegel on Sep 24, 2019

I encountered the same issue! I had to use the following to determine the output shape: shape_o1 = layer1.compute_output_shape(input_shape)

lukasbrunke on May 30, 2017