tf_cnnvis icon indicating copy to clipboard operation
tf_cnnvis copied to clipboard

Deconvolution is super slow

Open kitovyj opened this issue 6 years ago • 3 comments

Hello all.

Thank you for a great tool. I wonder, is there any way to speed up the computations? Layer deconvolution takes ~7 seconds in my case and I want to calculate deconvolutions for around ~10k examples, the network is of 7 layers.

BR, Alexander

kitovyj avatar Sep 22 '18 17:09 kitovyj

You could run the experiment in batches. Using a large batch size would be useful here to speed up the computations. We haven't experimented extensively with this, but the outputs of a batch would get written to disk together in an image. Let us know if this helps.

falaktheoptimist avatar Sep 26 '18 05:09 falaktheoptimist

Hmm, when I feed a batch with multiple inputs, the tool still generates a single image for each layer... I don't understand the principle here.

kitovyj avatar Sep 27 '18 21:09 kitovyj

Hi @kitovyj We are working on this. We'll roll out a version where you should be able to insert multiple images simultaneously. You are right - we revisited the code and in its current state it would return just the first image output.

falaktheoptimist avatar Oct 27 '18 11:10 falaktheoptimist