model-optimization

model-optimization copied to clipboard

Replace `tensorflow.python.keras` with `keras`. `tensorflow.python.keras` is an old copy and is deprecated.

copybara-service[bot]

Switches Keras object serialization to new logic and changes public API for deserialize_keras_object/serialize_keras_object to the new functions.

copybara-service[bot]

Custom layer with Concat afterwards causes an error during QAT modeling

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...

mhyeonsoo

Cannot use Quantize layer and use abstract class and methods

1

I am trying to Quantize the whole model but whenever, I try to load the model using quantized scope it gives me error like this ``` import sys, os import...

dhruven-god

Any plans to support keras3?

5

**System information** - TensorFlow version (you are using): 2.12.0 - Are you willing to contribute it (Yes/No): Yes **Motivation** Keras3 is the latest version and it supports multiple backends including...

Krovatkin

Fix model loading from .keras files in Tensorflow 2.15

1

When loading models from .keras files, quantize layer weight number does not match stored number of weights as layer is build twice. In addition, the QuantizeWrapperV2 does not populate the...

MaierOli2010

Pruning fails for siamese networks

4

**Describe the bug** Follow along with [MNIST siamese](https://keras.io/examples/mnist_siamese/), where one set of weights is used twice in the same network. Try to make one layer prune, get error: `tensorflow.python.framework.errors_impl.InvalidArgumentError: assertion...

cacfd3a

Error reported when prunning one tf-keras layer

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...

iamweiweishi

Per-tensor QAT model Conv2d+BN+relu folding issue

1

**Describe the bug** I need to train QAT (per-tensor) model and then convert it tflite. But I get "folding issue" described [here](https://github.com/tensorflow/model-optimization/issues/438#issuecomment-651229773). **System information** TensorFlow version (installed from source or...

sheh

**Describe the bug** Tensorflow model optimization fails to quantize dilated convolution layers. **System information** TensorFlow version (installed from source or binary): source TensorFlow Model Optimization version (installed from source or...

Ebanflo42