model-optimization

model-optimization copied to clipboard

Sparsity Runtime Integration with TF/TFLite for Latency Improvements

30

As suggested [here](https://www.tensorflow.org/model_optimization/guide/pruning), model pruning currently only provides benefits in model compression/size reduction. Further framework support is necessary to provide latency improvements in TF/TFLite.

alanchiao

[clustering] Possible wrong call of the centroids initializer from the ClusterWeights wrapper

1

An instance of the centroids initializer [expects](https://github.com/tensorflow/model-optimization/blob/v0.7.1/tensorflow_model_optimization/python/core/clustering/keras/clustering_centroids.py#L47) to be initialized with `data_format`. However, instead of `data_format` it gets `num_channels` here: https://github.com/tensorflow/model-optimization/blob/v0.7.1/tensorflow_model_optimization/python/core/clustering/keras/cluster_wrapper.py#L218 I suppose that line is erroneous. This may cause...

aserenko

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...

MounikaVaddeboina

Basic implementation for ternarization

copybara-service[bot]

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...

didadida-r

Typo Fix in Quantization Training Example

2

Duplicate 'for' word in code block comment.

CedArctic

Support for the LSTMPeephole package has been removed in response to its removal from keras. However, the tensorflow-optimization package has not been updated in Pypi. One of my models relies...

rsanthanam-amd

loc("model/FPN/FPN/FPN//Concatenate_p_1/concat"): error: 'tfl.concatenation' op quantization parameters violate the same scale constraint: !quant.uniform<i8:f32, 9.9999999999999995E-7> vs. !quant.uniform<i8:f32, 4.9130543629871681E-5:-128>

6

### 1. System information - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 20.04 - TensorFlow installation (pip package or built from source): pip - TensorFlow library (version, if...

YannPourcenoux

Internal change

copybara-service[bot]

Issue with loading quantization aware trained model

13

**Describe the bug** Unable to load the saved model after applying quantization aware training. **System information** TensorFlow version (installed from source or binary): 2.2 TensorFlow Model Optimization version (installed from...

peri044