Silk_760

It is impossible to have more parameters than the original one. maybe if you share the code, I can help you to know what is the problem is

it can be compressed yes, but the model will lose a significant accuracy. I have tried with another type of pruning, GANS and VAE are not as robust as CNNs....

I have the same issue, I have tried everything here and I still had the same issue ModuleNotFoundError: No module named 'libpymo'

> I did and this is my path ['', '/content', '/env/python', '/usr/lib/python37.zip', '/usr/lib/python3.7', '/usr/lib/python3.7/lib-dynload', '/usr/local/lib/python3.7/dist-packages', '/usr/lib/python3/dist-packages', '/usr/local/lib/python3.7/dist-packages/IPython/extensions', '/root/.ipython', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/'] I mean I tried everything and I always...

> > > > > > > > > I did and this is my path ['', '/content', '/env/python', '/usr/lib/python37.zip', '/usr/lib/python3.7', '/usr/lib/python3.7/lib-dynload', '/usr/local/lib/python3.7/dist-packages', '/usr/lib/python3/dist-packages', '/usr/local/lib/python3.7/dist-packages/IPython/extensions', '/root/.ipython', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu', '/usr/local/lib/python3.7/dist-packages/aimet_common/x86_64-linux-gnu/aimet_tensor_quantizer-0.0.0-py3.6-linux-x86_64.egg/']...

You should finetune the model first after the pruning, what happens to the model after the pruning removing the filters, in which the features maps are removed as well then...

> @Silk760 @quic-ssiddego I forgot to reply back to this thread. All of these recommendations are valid point and by the time that I posted this issues, I have already...

> @Silk760 If you can share with me that paper, it would be great. I'm very new to the model compression idea and any resource will be helpful. Thanks 😃...

https://arxiv.org/pdf/1803.03635.pdf Look at this

> Hi @badrid75 could please use [version 1.14.0](https://github.com/quic/aimet/releases/tag/1.14.0) for now? We're working on updating the instructions for the latest 1.16.0 release. Also the use of Code Colab is currently broken...