tensorflow/model-optimization

View on GitHub

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Stars: 1.6k
Forks: 349
Open beginner issues: 1
Indexed issues: 201
Avg merge: 3d 2h
Merged PRs (30d): 1

Dominant language: Python
License: Apache-2.0
Last GitHub push: Aug 24, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed

Beginner friendly Everything

Open All

201 open issues indexed

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

bug

tensorflow/model-optimization#1030 · 1 comment · 1 assignee · Opened Dec 2, 2022
'Pruning in Keras' Example: Unable to fine-tune pruned model on GPU (TF 2.9.2) Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

tensorflow/model-optimization#1026 · 5 comments · Opened Nov 10, 2022
Model Pruning with Yolo Object Detection Model Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

tensorflow/model-optimization#1018 · 1 comment · Opened Oct 28, 2022
Pruning error for transfer learning models from TF/Keras API Open

bug

tensorflow/model-optimization#1017 · 2 comments · 1 assignee · Opened Oct 13, 2022
Post training quantize TTS model fastspeech2 and failed Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#1010 · 5 comments · Opened Aug 23, 2022
Input and resource quantization Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 25/100

tensorflow/model-optimization#1003 · 1 comment · Opened Jul 28, 2022
Post-training integer quantization for SSDMobileNet - poor detection accuracy Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#1002 · 7 comments · Opened Jul 26, 2022
bilinear upsampling layer cannot be 8-bit quantized correctly Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 28/100

tensorflow/model-optimization#1000 · 3 comments · Opened Jul 23, 2022
about the Quantize layer when trans model Open

tensorflow/model-optimization#997 · 2 comments · 1 assignee · Opened Jul 20, 2022
QAT for subclass inside the subclass Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 28/100

tensorflow/model-optimization#996 · 2 comments · Opened Jul 19, 2022
Allow quantization of tied weights Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

tensorflow/model-optimization#994 · 2 comments · Opened Jul 13, 2022
Quantization aware training for a Transfer Learning MobileNet model Open

tensorflow/model-optimization#991 · 5 comments · 1 assignee · Opened Jul 13, 2022
Non-uniform sparsity layer-wise with PolynomialDecay scheduler Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 35/100

tensorflow/model-optimization#987 · 2 comments · Opened Jul 6, 2022
Trying to quantise MobileNetv3 small Exception encountered when calling layer "tf.__operators__.add_137" Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 30/100

tensorflow/model-optimization#980 · 8 comments · Opened Jun 10, 2022
PCQAT not working if Conv2D has kernel size 1x1 Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 38/100

tensorflow/model-optimization#979 · 8 comments · Opened Jun 9, 2022
How to extract original model's weight from trained QAT model? Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#977 · 9 comments · Opened Jun 6, 2022
Strange behaviour pruning with small datasets Open

bug

tensorflow/model-optimization#975 · 4 comments · 1 assignee · Opened Jun 3, 2022
Full Int8 QAT not working Open

bug

Difficulty 5/5 Over a week Newbie friendliness 20/100

tensorflow/model-optimization#974 · 13 comments · Opened May 25, 2022
Pruning only works for small batch sizes Open

bug

tensorflow/model-optimization#973 · 4 comments · 1 assignee · Opened May 25, 2022
How to apply tfmot to a non tf.keras.Model type model.. Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

tensorflow/model-optimization#968 · 4 comments · Opened May 10, 2022
Unable to use strip_pruning for subclass model Open

bug

Difficulty 5/5 Over a week Newbie friendliness 25/100

tensorflow/model-optimization#965 · 7 comments · Opened Apr 29, 2022
QAT model saving bug: Unable to save function b'__inference_separable_conv2d_layer_call_fn_961' Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

tensorflow/model-optimization#964 · 15 comments · Opened Apr 18, 2022
Stripping Quantized Model Open

bug

Difficulty 5/5 Over a week Newbie friendliness 25/100

tensorflow/model-optimization#958 · 1 comment · Opened Apr 9, 2022
Support Quantizing a tf.keras Model inside another tf.keras Model Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

tensorflow/model-optimization#957 · Opened Apr 8, 2022
Quantize naive !!! Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#956 · Opened Apr 4, 2022
Unable to prune/quantize multiple layers at the same time Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 28/100

tensorflow/model-optimization#955 · Opened Mar 30, 2022
Unable to quantize to 4-bits Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 35/100

tensorflow/model-optimization#950 · Opened Mar 18, 2022
prune_low_magnitude fail when wrapped with GRU layer, but success with conv2d and dense Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#944 · Opened Mar 15, 2022
QAT support for LayerNormalization Open

feature request technique:qat

tensorflow/model-optimization#942 · 1 assignee · Opened Mar 11, 2022
Unsupported operations when applying tfmot Open

bug

tensorflow/model-optimization#941 · 1 comment · 1 assignee · Opened Mar 4, 2022
Not able to cluster Conv1DTranspose layer Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 30/100

tensorflow/model-optimization#940 · 3 comments · Opened Mar 3, 2022
[clustering] Possible wrong call of the centroids initializer from the ClusterWeights wrapper Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 48/100

tensorflow/model-optimization#939 · 1 comment · Opened Mar 1, 2022
LSTMPeephole package removed: Pypi not updated Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 20/100

tensorflow/model-optimization#938 · Opened Feb 24, 2022
Support for tensorflow hub layers Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 35/100

tensorflow/model-optimization#924 · 1 comment · Opened Jan 21, 2022
GELU - Keras Layer Open

feature request

tensorflow/model-optimization#922 · 1 assignee · Opened Jan 18, 2022
the API doc of prune_low_magnitude seems to be incomplete Open

tensorflow/model-optimization#901 · 1 comment · 1 assignee · Opened Dec 20, 2021
How to use default n bit in QAT ? Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 20/100

tensorflow/model-optimization#885 · 3 comments · 1 reaction · Opened Nov 16, 2021
QAT with trainable=False does not work as expected. Open

bug

tensorflow/model-optimization#881 · 7 comments · 1 reaction · 1 assignee · Opened Nov 10, 2021
How to prune a custom tensor? The tensor is a recursive variable and is initialized with tf.zeros. Open

bug

tensorflow/model-optimization#875 · 3 comments · 1 assignee · Opened Nov 1, 2021
Quantizing model at runtime during training results in non-learned quantization Open

bug

tensorflow/model-optimization#869 · 1 comment · 1 assignee · Opened Oct 26, 2021
QAT model saving bug : KeyError: '__inference_depthwise_conv2d_layer_call_fn_126 Open

bug

tensorflow/model-optimization#868 · 19 comments · 1 reaction · 1 assignee · Opened Oct 22, 2021
Keras TFOpLambda may conflict with quantization Open

bug

tensorflow/model-optimization#867 · 12 comments · 1 reaction · 1 assignee · Opened Oct 22, 2021
Pruning error of transfer learning model MobilenetV3 Large ! Open

bug

tensorflow/model-optimization#864 · 1 comment · 1 assignee · Opened Oct 14, 2021
Set zero_debias=True for Quantization Aware Training Open

tensorflow/model-optimization#863 · 3 comments · 1 assignee · Opened Oct 8, 2021
Issue for the FAKE_QUANT result Open

tensorflow/model-optimization#858 · 4 comments · 1 assignee · Opened Oct 5, 2021
quantizing to int values Open

tensorflow/model-optimization#853 · 2 comments · 1 assignee · Opened Sep 30, 2021
Segmentation fault when invoking TFLite interpreter on basic quantized model Open

Difficulty 4/5 3-5 days Newbie friendliness 25/100

tensorflow/model-optimization#857 · 1 comment · Opened Sep 29, 2021
Activity Regularizer not working with quantization aware training (QAT) TF 2.6 Open

tensorflow/model-optimization#842 · 4 comments · 19 reactions · 1 assignee · Opened Sep 27, 2021
Fix the integration of TFLite models with multiple signatures and quantization Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

tensorflow/model-optimization#843 · 1 comment · Opened Sep 26, 2021
problem with quantizing the BN layer Open

tensorflow/model-optimization#841 · 6 comments · 1 assignee · Opened Sep 26, 2021

tensorflow/model-optimization

Get new issues in your inbox