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

Broken pre-optimized models link in getting-started guide Open

Difficulty 2/5 1-3 hours Newbie friendliness 74/100

tensorflow/model-optimization#1301 · 1 comment · Opened Sep 6, 2026
tensorflow-model-optimization fails to import in official tensorflow:2.15.0 Docker image due to TF_USE_LEGACY_KERAS=1 and missing tf_keras Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 48/100

tensorflow/model-optimization#1272 · Opened Mar 24, 2026
quantize_model() rejects a valid standalone Keras 3 Sequential model Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 50/100

tensorflow/model-optimization#1270 · 2 comments · Opened Mar 23, 2026
build from source fails on macos Open

bug

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

tensorflow/model-optimization#1241 · Opened Jan 7, 2026
First Conv2D layer in model cannot be pruned with structured sparsity (sparsity_m_by_n) Open

bug

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

tensorflow/model-optimization#1182 · 1 comment · Opened Jun 14, 2025
ValueError: `to_annotate` can only be a `keras.layers.Layer` instance. You passed an instance of type: Dense. Open

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

tensorflow/model-optimization#1181 · 1 comment · Opened Jun 12, 2025
ValueError: `to_annotate` can only be a `keras.layers.Layer` instance. You passed an instance of type: Dense. Open

Difficulty 3/5 1-2 days Newbie friendliness 55/100

tensorflow/model-optimization#1180 · 1 comment · Opened Jun 12, 2025
Incorrect inputs reordering inside `ModelTransformer._get_layers` during pattern matchin Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 45/100

tensorflow/model-optimization#1179 · 2 comments · Opened Apr 22, 2025
Any plans to update numpy to v2 Open

feature request

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

tensorflow/model-optimization#1177 · 1 comment · 10 reactions · Opened Feb 27, 2025
MAC operations in the pruned model??? Open

Difficulty 5/5 Over a week Newbie friendliness 10/100

tensorflow/model-optimization#1176 · Opened Feb 11, 2025
ValueError: `prune_low_magnitude` can only prune an object of the following types: keras.models.Sequential, keras functional model, keras.layers.Layer, list of keras.layers.Layer. You passed an object of type: Conv2D. Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 38/100

tensorflow/model-optimization#1172 · 1 comment · Opened Jan 19, 2025
ValueError: `prune_low_magnitude` can only prune an object of the following types: keras.models.Sequential, keras functional model, keras.layers.Layer, list of keras.layers.Layer. You passed an object of type: Sequential. Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

tensorflow/model-optimization#1167 · 2 comments · Opened Dec 1, 2024
Unexpected error when performing QAT on some layers of a GNN model. Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 45/100

tensorflow/model-optimization#1166 · 1 comment · Opened Nov 29, 2024
TFOpLambda not supported in INT8 Quantization Aware Training (Mobilenetv3) Open

bug

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

tensorflow/model-optimization#1145 · 1 comment · Opened Oct 8, 2024
quantize_model() cannot detect a keras.Sequential model Open

bug

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

tensorflow/model-optimization#1144 · 3 comments · Opened Oct 8, 2024
Requirements.txt allows an unsupported version of tf+keras Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

tensorflow/model-optimization#1143 · 2 reactions · Opened Oct 2, 2024
Failed to apply the QAT function 'quantize_model' to the sequential model that is defined using tensorflow.keras Open

bug

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

tensorflow/model-optimization#1140 · 3 comments · Opened Jul 26, 2024
RuntimeError: Layer tf.__operators__.getitem:<class 'tf_keras.src.layers.core.tf_op_layer.SlicingOpLambda'> is not supported. Open

feature request

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

tensorflow/model-optimization#1139 · Opened Jul 9, 2024
Unexpected Inference Time and Model Size for TensorFlow Lite and Pruned Models Open

bug

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

tensorflow/model-optimization#1135 · Opened Jun 21, 2024
Is it possible to use this tool to optimize (quantize) a model trained with PyTorch? Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 15/100

tensorflow/model-optimization#1134 · Opened Jun 20, 2024
Does structural pruning support pre-trained model? Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 15/100

tensorflow/model-optimization#1133 · Opened Jun 9, 2024
DepthwiseConv2D Layers cannot be clustered or sparsely pruned Open

bug

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

tensorflow/model-optimization#1132 · Opened Jun 6, 2024
Per-tensor QAT model Conv2d+BN+relu folding issue Open

bug

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

tensorflow/model-optimization#1131 · 1 comment · Opened May 15, 2024
Failed quantization of dilated convolution layers: tensorflow or tensorflow-model-optimization bug? Open

bug

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

tensorflow/model-optimization#1130 · Opened May 13, 2024
Custom layer with Concat afterwards causes an error during QAT modeling Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

tensorflow/model-optimization#1124 · 3 comments · Opened Mar 27, 2024
Cannot use Quantize layer and use abstract class and methods Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

tensorflow/model-optimization#1122 · 1 comment · Opened Feb 26, 2024
Any plans to support keras3? Open

feature request

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

tensorflow/model-optimization#1119 · 5 comments · 6 reactions · Opened Feb 20, 2024
Can't use TFMOT version 0.8.0 due to missing dependency Open

bug

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

tensorflow/model-optimization#1117 · 1 comment · 11 reactions · Opened Feb 12, 2024
Support for Recurrent layers for Quantization Aware Training. Open

feature request

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

tensorflow/model-optimization#1114 · 1 comment · Opened Feb 6, 2024
strange behavior when quantizing a model. Open

bug

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

tensorflow/model-optimization#1109 · 2 comments · Opened Jan 23, 2024
Error in MovingAverageQuantizer with per_axis=True due to missing parameters in _add_range_weights Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 55/100

tensorflow/model-optimization#1108 · Opened Jan 23, 2024
MobileNetV3 QAT TFLite Conversion Issue Open

bug

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

tensorflow/model-optimization#1107 · 7 comments · Opened Jan 15, 2024
Add batch norm to default_n_bit_quantize_registry and default_8_bit_quantize_registry Open

feature request

Difficulty 2/5 1-3 hours Newbie friendliness 42/100

tensorflow/model-optimization#1099 · 2 comments · 1 reaction · Opened Sep 28, 2023
Add a default PruningPolicy that filters out any layers not supported by the API Open

feature request

tensorflow/model-optimization#1098 · 1 comment · 1 assignee · Opened Sep 26, 2023
float16 quantization runs out of memory for LSTM model Open

bug

tensorflow/model-optimization#1091 · 3 comments · 1 assignee · Opened Aug 30, 2023
16x8 Quantization fails for RNN model - Max and min for dynamic tensors should be recorded during calibration Open

bug

tensorflow/model-optimization#1090 · 4 comments · 2 assignees · Opened Aug 30, 2023
QAT aware training for mobilenetV2 not working Open

tensorflow/model-optimization#1086 · 1 comment · 1 assignee · Opened Aug 17, 2023
AttributeError: 'CustomLayerMaxPooling1D' object has no attribute 'kernel' Open

feature request

tensorflow/model-optimization#1085 · 1 comment · 1 assignee · Opened Aug 16, 2023
Custom_Layer Quantization with custom training (QAT) Open

bug

tensorflow/model-optimization#1084 · 2 comments · 1 assignee · Opened Aug 14, 2023
Cannot `pip install` nightly Open

bug

tensorflow/model-optimization#1079 · 2 comments · 1 assignee · Opened Jun 28, 2023
Cannot save pruned model with MultiHeadAttention Layer Open

bug

tensorflow/model-optimization#1077 · 2 comments · 1 assignee · Opened Jun 27, 2023
trainable=False doesn't work for QuantizeWrapperV2 Open

bug

tensorflow/model-optimization#1067 · 1 comment · 1 reaction · 1 assignee · Opened May 2, 2023
Does Post-training full integer quantization support BERT? Open

bug

tensorflow/model-optimization#1066 · 1 comment · 1 assignee · Opened Apr 27, 2023
some questions about quantization in TensorFlow Open

tensorflow/model-optimization#1064 · 1 assignee · Opened Apr 26, 2023
Stripping disconnects input layer from graph Open

bug

tensorflow/model-optimization#1063 · 1 assignee · Opened Apr 25, 2023
`tf.split` or `tf.transpose` cause errors for quantize-aware training with `quantize_apply` Open

bug

tensorflow/model-optimization#1062 · 4 comments · 1 assignee · Opened Apr 20, 2023
The input order of concatenate layer is changed, when use quantize_model interface. Open

bug

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

tensorflow/model-optimization#1061 · 1 comment · Opened Apr 18, 2023
CQAT fails to preserve clusters on ResNet-50 Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 42/100

tensorflow/model-optimization#1056 · 1 comment · Opened Apr 14, 2023
Consider reorganizing file layout to shorten path lengths Open

bug

tensorflow/model-optimization#1032 · 1 assignee · Opened Dec 8, 2022
A error when using tfmot.quantization.keras.quantize_model to quantize keras model Open

bug

tensorflow/model-optimization#1031 · 2 comments · 1 assignee · Opened Dec 7, 2022

tensorflow/model-optimization

Get new issues in your inbox