model-optimization

model-optimization copied to clipboard

Remove optimizer to compare model size and compare the zipped model size to pass the test. And enable test because now it passed.

copybara-service[bot]

Post training quantize TTS model fastspeech2 and failed

5

Hi Everyone, I tried to post quantize fastspeech2 model of TensorFlowTTS ,but got the error message, I was wondering if anyone knows the detials of this error and how to...

zhuyu14

Internal change

copybara-service[bot]

Updates security files

copybara-service[bot]

Can't use TFMOT version 0.8.0 due to missing dependency

1

**Describe the bug** Can't use latest TFMOT 0.8.0 with the latest TF 2.15.0.post1 on a fresh install because of missing `tf_keras` dependency. This complicates installations of downstream packages that depend...

vloncar

strange behavior when quantizing a model.

2

Hi all, I was trying to quantize my model but something strange popped up. I am using TensorFlow v2.14 and tfmot v0.7.5 I have a sub-classed tf.Keras.Model. It contains some...

IdrissARM

Support for Recurrent layers for Quantization Aware Training.

1

**System information** - TensorFlow version (you are using): 2.15 - Are you willing to contribute it (Yes/No): Yes **Motivation** I am trying to train RNN model with quantization aware training...

parth-desai

Update documentation in quantize.py

1

TheCrazyT

16x8 Quantization fails for RNN model - Max and min for dynamic tensors should be recorded during calibration

4

Doing 16x8 quantization on RNN models fails. **Code to reproduce the issue** [gist to reproduce the issue on Google Colab](https://colab.research.google.com/drive/1tkXarTrLDA468U1AKXbs6yqdrPcfIsZj?usp=sharing) Code: ```python import numpy as np import tensorflow as tf...

AminHasanpour

**Describe the bug** Using the `MovingAverageQuantizer` with parameter `per_axis` set to True results in this error: > tensorflow_model_optimization\python\core\quantization\keras\quant_ops.py", line 335, in _FakeQuantWithMinMaxVars * > assert len(min_var.get_shape()) == 1 It's caused...

Litschi123