model-optimization

model-optimization copied to clipboard

Cannot `pip install` nightly

2

**Describe the bug** Cannot `pip install` nightly version of this package **System information** TensorFlow version (installed from source or binary): none TensorFlow Model Optimization version (installed from source or binary):...

christian-steinmeyer

AttributeError: 'CustomLayerMaxPooling1D' object has no attribute 'kernel'

1

Hi, when I am trying Quantization Aware Training on my model, I get the following error in my 'CustomLayerMaxPooling1D' : --------------------------------------------------------------------------- AttributeError Traceback (most recent call last) Cell In [62],...

konstantinatopali

QAT aware training for mobilenetV2 not working

1

Hello I am trying to apply quantization aware training for mobilenet, and I am testing on the mnist dataset, the floating point models works very well but the moment I...

christophezeinaty

Custom_Layer Quantization with custom training (QAT)

2

**Describe the bug** Unable to quantize the custom layer to Int8 even after quantization. **System information** TensorFlow version (installed from source or binary): 2.15.0-dev20230814 TensorFlow Model Optimization version (installed from...

ManishwarG

trainable=False doesn't work for QuantizeWrapperV2

1

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...

jiannanWang

If there are multiple input layers (and therefore paths), this early out might return an empty set before all paths are checked. By simply removing it, the path that doesn't...

christian-steinmeyer

add original weight name as prefix for mask and threshold weights

1

If there are multiple prunable weights in a wrapped layer, without this change, the wrapped model cannot be saved to h5 because of duplicate dataset names (the layer has multiple...

christian-steinmeyer

This aids downstream repos that implement fixes for various cloning issues by making this function able to be monkey-patched. For context, I am part of @hunse's team that is affected...

tbekolay

Internal test

copybara-service[bot]

A error when using tfmot.quantization.keras.quantize_model to quantize keras model

2

**Describe the bug** When quantizing the keras model after pruning, an error is reported as follows. RuntimeError: Layer conv1d: is not supported. You can quantize this layer by passing a...

DuJiahao1996