model-optimization

model-optimization copied to clipboard

Fail to fuse ReLU6 after QAT by using keras.layers.Activation('relu6')

1

**Describe the bug** ReLU6 cannot be fused into Conv2D (Conv2D+BN+ReLU6) after QAT by using `keras.layers.Activation('relu6')` Following works fine: - `keras.layers.ReLU(6)` - `keras.layers.Activation('relu')` - `keras.layers.ReLU()` So the workaround is to stick...

james77777778

Creates non-breaking changes where necessary in preparation for switching all of Keras to new serialization format.

copybara-service[bot]

Cast using FunctionType instead of input_signature

copybara-service[bot]

Changes external references to `keras.utils.serialize_keras_object/deserialize_keras_object` to legacy serialization API in preparation for switching all of Keras to new serialization format.

copybara-service[bot]

**Describe the bug** The current package includes path names upwards of 150 characters such as [`default_8bit_cluster_preserve_quantize_scheme.py`](https://github.com/tensorflow/model-optimization/blob/master/tensorflow_model_optimization/python/core/quantization/keras/collaborative_optimizations/cluster_preserve/default_8bit_cluster_preserve_quantize_scheme.py) which are in turn relatively short files deep in a hierarchy. On Windows, the...

scdub

Update comprehensive_guide.ipynb

1

The broken link to "enable pruning to improve latency" has been fixed in line 726, and the typos at lines 590 and 390 are fixed.

synandi

Support for Multiply layer

1

**System information** - TensorFlow version (you are using): 2.4.1 - Are you willing to contribute it (Yes/No): no **Motivation** The implementation of some models (e.g. SENet) requires the use of...

FSet89

Change PruningSummaries to only log pruning information

copybara-service[bot]

Pruning error for transfer learning models from TF/Keras API

2

**System information** TensorFlow version (installed from source or binary): 2.10 TensorFlow Model Optimization version (installed from source or binary): 0.7.3 Python version: 3.8 **Bug** Hi, I have been experimenting with...

frost-is

Model Pruning with Yolo Object Detection Model

1

Is there any way to use tfmot for Keras Yolov3-v4 model pruning, or any other object detection model.

divyajaincs