model-optimization

model-optimization copied to clipboard

I converted my TensorFlow models (.h5 format) to TensorFlow Lite, including quantized and pruned versions. Note: my model is squeezenet Script to Save Lite Model: ```python def create_tflite_model(original_model): converter =...

experimentsym3

hello, I want to ask Is it possible to use this tool to optimize (quantize) a model trained with PyTorch or it only allowed the model trained with Keras ?...

zhuoran-guo

**System information** - TensorFlow version (you are using): - Are you willing to contribute it (Yes/No): **Motivation** What is the use case and how does it broadly benefits users? Prioritization...

aidevmin

When attempting to sparsely prune or cluster DepthwiseConv2D Layers it appears that no clustering or sparse pruning actually occurs. **System information** TensorFlow version (installed from source or binary): 2.16.1/2.15.1 TensorFlow...

nathanwbailey

Failed to apply the QAT function 'quantize_model' to the sequential model that is defined using tensorflow.keras

3

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...

wwwind

**System information** - TensorFlow version (you are using): 2.15.1 - tf-keras version (you are using): 2.15.1 - tensorflow_model_optimization version (you are using): 0.8.0 - Are you willing to contribute it...

reganh98

TFOpLambda not supported in INT8 Quantization Aware Training (Mobilenetv3)

1

**Describe the bug** I cannot quantize Mobilenetv3 from keras2 because the hard-swish activation fuction is implemented as a TFOpLambda. **System information** tensorflow version: 2.17 tf_keras version: 2.17 tensorflow_model_optimization version: 0.8.0...

pedrofrodenas

quantize_model() cannot detect a keras.Sequential model

3

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...

DKMaCS

**Describe the bug** The current requirements.txt allows for installation of Tensorflow and Keras versions that are not supported. The latest release (https://github.com/tensorflow/model-optimization/releases/tag/v0.8.0) needs Keras 2.x, which leads to bugs like...

zeroby0

**Bug Description** When applying structured pruning with sparsity_m_by_n parameter to a model containing multiple Conv2D layers, the first Conv2D layer consistently fails to be pruned while identical subsequent Conv2D layers...

anasvaf