Skip to content

Issues: tensorflow/model-optimization

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

191 Open 168 Closed
191 Open 168 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

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. bug Something isn't working
#1167 opened Dec 1, 2024 by RifatUllah102
Unexpected error when performing QAT on some layers of a GNN model. bug Something isn't working
#1166 opened Nov 29, 2024 by sicong-li-arm
TFOpLambda not supported in INT8 Quantization Aware Training (Mobilenetv3) bug Something isn't working
#1145 opened Oct 8, 2024 by pedrofrodenas
1
quantize_model() cannot detect a keras.Sequential model bug Something isn't working
#1144 opened Oct 8, 2024 by DKMaCS
3
Requirements.txt allows an unsupported version of tf+keras bug Something isn't working
#1143 opened Oct 2, 2024 by zeroby0
Failed to apply the QAT function 'quantize_model' to the sequential model that is defined using tensorflow.keras bug Something isn't working
#1140 opened Jul 26, 2024 by wwwind
3
RuntimeError: Layer tf.__operators__.getitem:<class 'tf_keras.src.layers.core.tf_op_layer.SlicingOpLambda'> is not supported. feature request feature request
#1139 opened Jul 9, 2024 by reganh98
Unexpected Inference Time and Model Size for TensorFlow Lite and Pruned Models bug Something isn't working
#1135 opened Jun 21, 2024 by experimentsym3
Is it possible to use this tool to optimize (quantize) a model trained with PyTorch? feature request feature request
#1134 opened Jun 20, 2024 by zhuoran-guo
Does structural pruning support pre-trained model? feature request feature request
#1133 opened Jun 9, 2024 by aidevmin
DepthwiseConv2D Layers cannot be clustered or sparsely pruned bug Something isn't working
#1132 opened Jun 6, 2024 by nathanwbailey
Per-tensor QAT model Conv2d+BN+relu folding issue bug Something isn't working
#1131 opened May 15, 2024 by sheh
Failed quantization of dilated convolution layers: tensorflow or tensorflow-model-optimization bug? bug Something isn't working
#1130 opened May 13, 2024 by Ebanflo42
Custom layer with Concat afterwards causes an error during QAT modeling bug Something isn't working
#1124 opened Mar 27, 2024 by mhyeonsoo
3
Cannot use Quantize layer and use abstract class and methods bug Something isn't working
#1122 opened Feb 26, 2024 by dhruven-god
1
Any plans to support keras3? feature request feature request
#1119 opened Feb 20, 2024 by Krovatkin
5
Can't use TFMOT version 0.8.0 due to missing dependency bug Something isn't working
#1117 opened Feb 12, 2024 by vloncar
1
Support for Recurrent layers for Quantization Aware Training. feature request feature request
#1114 opened Feb 6, 2024 by parth-desai
1
strange behavior when quantizing a model. bug Something isn't working
#1109 opened Jan 23, 2024 by IdrissARM
2
Error in MovingAverageQuantizer with per_axis=True due to missing parameters in _add_range_weights bug Something isn't working
#1108 opened Jan 23, 2024 by Litschi123
MobileNetV3 QAT TFLite Conversion Issue bug Something isn't working
#1107 opened Jan 15, 2024 by tarushbansal
7
Add batch norm to default_n_bit_quantize_registry and default_8_bit_quantize_registry feature request feature request
#1099 opened Sep 28, 2023 by DerryFitz
2
Add a default PruningPolicy that filters out any layers not supported by the API feature request feature request
#1098 opened Sep 26, 2023 by annietllnd
@lenscloth
1
float16 quantization runs out of memory for LSTM model bug Something isn't working
#1091 opened Aug 30, 2023 by Black3rror
@yyoon
3
16x8 Quantization fails for RNN model - Max and min for dynamic tensors should be recorded during calibration bug Something isn't working
#1090 opened Aug 30, 2023 by Black3rror
@yyoon @tucan9389
4
ProTip! Find all open issues with in progress development work with linked:pr.