Prior to filing: check that this should be a bug instead of a feature request. Everything supported, including the compatible versions of TensorFlow, is listed in the overview page of each technique. For example, the overview page of quantization-aware training is here. An issue for anything not supported should be a feature request.
Describe the bug
CQAT does not preserve clusters. Training ResNet-50 with CIFAR-100
System information
TensorFlow version (installed from source or binary): TensorFlow 2.5
TensorFlow Model Optimization version (installed from source or binary): 0.7.3
Python version: 3.7.13
Describe the expected behavior
Model weight clusters are preserved after cluster preserving quantization aware training
Describe the current behavior
Model weight clusters are not preserved for some of the kernels after cluster preserving quantization aware training
Code to reproduce the issue
Provide a reproducible code that is the bare minimum necessary to generate the
problem.
Prior to filing: check that this should be a bug instead of a feature request. Everything supported, including the compatible versions of TensorFlow, is listed in the overview page of each technique. For example, the overview page of quantization-aware training is here. An issue for anything not supported should be a feature request.
Describe the bug CQAT does not preserve clusters. Training ResNet-50 with CIFAR-100
System information
TensorFlow version (installed from source or binary): TensorFlow 2.5
TensorFlow Model Optimization version (installed from source or binary): 0.7.3
Python version: 3.7.13
Describe the expected behavior Model weight clusters are preserved after cluster preserving quantization aware training
Describe the current behavior Model weight clusters are not preserved for some of the kernels after cluster preserving quantization aware training
Code to reproduce the issue Provide a reproducible code that is the bare minimum necessary to generate the problem.
Screenshots If applicable, add screenshots to help explain your problem.
Additional context Add any other context about the problem here.