search

MarvinTeichmann / tensorflow-fcn

An Implementation of Fully Convolutional Networks in Tensorflow.
MIT License
1.1k stars 433 forks source link

fcn16: ValueError: Incompatible shapes for broadcasting: (?, ?, ?, 2) and (?, ?, ?, 20) #8

Closed Thrasi closed 8 years ago

Thrasi commented 8 years ago

I run: python test_fcn16_vgg.py

And get: Traceback (most recent call last): File "test_fcn16_vgg.py", line 36, in <module> vgg_fcn.build(batch_images, debug=True) File "/home/***/misc/tensorflow-fcn/fcn16_vgg.py", line 125, in build self.fuse_pool4 = tf.add(self.upscore2, self.score_pool4) ... ValueError: Incompatible shapes for broadcasting: (?, ?, ?, 2) and (?, ?, ?, 20)

Examination of _upscore_layer for the three network architectures shows that the function in fcn16_vgg.py includes a line at 237:

deconv.set_shape([None, None, None, 2])

which is hard coded for 2 classes. This line should be removed I assume. The code runs after I remove it.

MarvinTeichmann commented 8 years ago

You are right. This line was absolutely unnecessary. There is no need to set the shape of deconv at all. No idea how it got there. Thx