tensorflow/model-optimization

Issues

• 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.

  #1167 opened 24 days ago by RifatUllah102
  0

• Unexpected error when performing QAT on some layers of a GNN model.

  #1166 opened 25 days ago by sicong-li-arm
  0

• Any plans to support keras3?

  #1119 opened 10 months ago by Krovatkin
  5

• quantize_model() cannot detect a keras.Sequential model

  #1144 opened 3 months ago by DKMaCS
  3

• TFOpLambda not supported in INT8 Quantization Aware Training (Mobilenetv3)

  #1145 opened 3 months ago by pedrofrodenas
  1

• Requirements.txt allows an unsupported version of tf+keras

  #1143 opened 3 months ago by zeroby0
  0

• Failed to apply the QAT function 'quantize_model' to the sequential model that is defined using tensorflow.keras

  #1140 opened 5 months ago by wwwind
  2

• Determinism is not yet supported in GPU implementation of FakeQuantWithMinMaxVarsGradient

  #1087 opened a year ago by puelon
  3

• 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.

  #1141 opened 5 months ago by FrancescoSorrentino
  1

• MobileNetV3 QAT TFLite Conversion Issue

  #1107 opened a year ago by tarushbansal
  7

• Add batch norm to default_n_bit_quantize_registry and default_8_bit_quantize_registry

  #1099 opened a year ago by DerryFitz
  2

• Cannot use Quantize layer and use abstract class and methods

  #1122 opened 10 months ago by dhruven-god
  1

• Custom layer with Concat afterwards causes an error during QAT modeling

  #1124 opened 9 months ago by mhyeonsoo
  3

• RuntimeError: Layer tf.__operators__.getitem:<class 'tf_keras.src.layers.core.tf_op_layer.SlicingOpLambda'> is not supported.

  #1139 opened 6 months ago by reganh98
  0

• Unexpected Inference Time and Model Size for TensorFlow Lite and Pruned Models

  #1135 opened 6 months ago by experimentsym3
  0

• Is it possible to use this tool to optimize (quantize) a model trained with PyTorch?

  #1134 opened 6 months ago by zhuoran-guo
  0

• Does structural pruning support pre-trained model?

  #1133 opened 7 months ago by aidevmin
  0

• DepthwiseConv2D Layers cannot be clustered or sparsely pruned

  #1132 opened 7 months ago by nathanwbailey
  0

• Per-tensor QAT model Conv2d+BN+relu folding issue

  #1131 opened 7 months ago by sheh
  0

• Failed quantization of dilated convolution layers: tensorflow or tensorflow-model-optimization bug?

  #1130 opened 7 months ago by Ebanflo42
  0

• float16 quantization runs out of memory for LSTM model

  #1091 opened a year ago by Black3rror
  3

• Support for Recurrent layers for Quantization Aware Training.

  #1114 opened a year ago by parth-desai
  1

• 16x8 Quantization fails for RNN model - Max and min for dynamic tensors should be recorded during calibration

  #1090 opened a year ago by Black3rror
  4

• Quant aware training in tensorflow model optimization

  #1100 opened 9 months ago by ardeal
  4

• Can't use TFMOT version 0.8.0 due to missing dependency

  #1117 opened 10 months ago by vloncar
  1

• `tf.split` or `tf.transpose` cause errors for quantize-aware training with `quantize_apply`

  #1062 opened 2 years ago by Janus-Shiau
  4

• strange behavior when quantizing a model.

  #1109 opened a year ago by IdrissARM
  2

• Error in MovingAverageQuantizer with per_axis=True due to missing parameters in _add_range_weights

  #1108 opened a year ago by Litschi123
  0

• A error about quantization aware training

  #1105 opened a year ago by panhu
  2

• Module Import Error

  #1104 opened a year ago by surajpandey353
  2

• [COLAB] No module named 'tensorflow_model_optimization'

  #1101 opened a year ago by rjtp5670
  1

• Cannot save pruned model with MultiHeadAttention Layer

  #1077 opened a year ago by christian-steinmeyer
  2

• Add a default PruningPolicy that filters out any layers not supported by the API

  #1098 opened a year ago by annietllnd
  1

• Cannot prune models with tensorflow operations

  #1051 opened 2 years ago by useruser2023
  6

• tfl.concatenation op quantization parameters violate the same scale constraint

  #1053 opened a year ago by akrapukhin
  2

• Cannot `pip install` nightly

  #1079 opened a year ago by christian-steinmeyer
  2

• float16 quantization runs out of memory for LSTM model

  #1092 opened a year ago by Black3rror
  1

• batch norm layer quantization error

  #1089 opened a year ago by mhyeonsoo
  2

• AttributeError: 'CustomLayerMaxPooling1D' object has no attribute 'kernel'

  #1085 opened a year ago by konstantinatopali
  1

• QAT aware training for mobilenetV2 not working

  #1086 opened a year ago by christophezeinaty
  1

• Custom_Layer Quantization with custom training (QAT)

  #1084 opened a year ago by ManishwarG
  2

• trainable=False doesn't work for QuantizeWrapperV2

  #1067 opened 2 years ago by jiannanWang
  1

• Quantization introduces inconsistencies during distributed training

  #1068 opened 2 years ago by jiannanWang
  1

• A error when using tfmot.quantization.keras.quantize_model to quantize keras model

  #1031 opened 2 years ago by DuJiahao1996
  2

• Does Post-training full integer quantization support BERT?

  #1066 opened 2 years ago by MrRace
  1

• some questions about quantization in TensorFlow

  #1064 opened 2 years ago by rthenamvar
  0

• Stripping disconnects input layer from graph

  #1063 opened 2 years ago by christian-steinmeyer
  0

• CQAT fails to preserve clusters on ResNet-50

  #1056 opened 2 years ago by funkyyyyyy
  1

• The input order of concatenate layer is changed, when use quantize_model interface.

  #1061 opened 2 years ago by fhahaha
  1

• Consider reorganizing file layout to shorten path lengths

  #1032 opened 2 years ago by scdub
  0