search

GouravWadhwa / Hypergraphs-Image-Inpainting

(WACV 2021) Hyperrealistic Image Inpainting with Hypergraphs
90 stars 15 forks source link

Weights for the Hypergraph layers #3

Closed serizba closed 3 years ago

serizba commented 3 years ago

Hi,

Thanks for publishing this amazing work!

Executing your code I realized that in the way you are defining the hypergraphs, the convolutional layers' weights are not being added to the TensorFlow graph. That means that (if you use the code as is) you are not updating the convolutional weights in the hypergraph layer.

def call (self, x) :
   # New keras layers defined during the call are created on every different call
   # therefore are not included in the computational graph
   phi = tf.keras.layers.Conv2D(self.filters, ....)(x)
   ...

Actually, if you list all the weights contained in the checkpoints that you provide you can see that there is no weight that corresponds with the hypergraph convolutions. I don't know if this is a flaw or a desired behavior. If it is a flaw, perhaps you can even improve your results by fixing it.

Thanks

GouravWadhwa commented 3 years ago

Thanks for the note. I will take care of this in the next release.

Thank you Gourav