gan-compression icon indicating copy to clipboard operation
gan-compression copied to clipboard

gan compression on tensorflow

Open sepideh-srj opened this issue 4 years ago • 2 comments

Hi,

I wanted to implement GAN compression on TensorFlow so I can use it on a mobile application. I'm pretty new to this field and I'm not aware of the challenges of doing something like this might have. Should I implement the whole thing on Tensorflow myself? would it be as fast as it is in Pytorch? Or should I convert the pytorch model to tensorflow with onnx? I would really appreciate any help

sepideh-srj avatar Aug 21 '20 02:08 sepideh-srj

Cool! I think you could first convert the pytorch model to tensorflow with onnx first. I am not familiar with tensorflow, so currently I could not predict what kind of challenges you may meet. If you have any questions, feel free to open issues here.

lmxyy avatar Aug 23 '20 01:08 lmxyy

@sepideh-srj As far as i know, you can train and compress your model with Pytorch and than convert the Pytorch model to tensorflow or tflite model, it will be the simplest way.

NewCoderQ avatar Sep 21 '20 15:09 NewCoderQ