model-optimization

model-optimization copied to clipboard

MobileNetV3 QAT TFLite Conversion Issue

7

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...

tarushbansal

Pruning does not reduce inference time.

3

**System information** - TensorFlow version (you are using): 2.3.0 - Are you willing to contribute it (Yes/No): No **Motivation** Currently pruning in tensorflow_model_optimization  does not result in a reduction in...

ectg

Add batch norm to default_n_bit_quantize_registry and default_8_bit_quantize_registry

2

- TensorFlow version (you are using): 2.13 - **Motivation** There are many models which use batch norm in places where it is not covered by the existing cases allowed in...

DerryFitz

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

4

**Describe the bug** We are trying to implement some network like [ShuffleNetV2](https://arxiv.org/abs/1807.11164) but encounter some error when `quantize_apply` the model.  I believe ShuffleNet or related ideas are popular in...

Janus-Shiau

Cannot save pruned model with MultiHeadAttention Layer

2

**Describe the bug** Trying to save a model that wraps a `MultiHeadAttention` layer in a `PruneLowMagnitude`, fails with duplicate dataset name. **System information** TensorFlow version (installed from source or binary):...

christian-steinmeyer

Quant aware training in tensorflow model optimization

3

Hi, I did see post_training_quant in model optimization, however, I didn't see quant aware training tutorial or examples. is there quant aware training in model optimization? is there quant aware...

ardeal

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

1

Hi TFMOT team! I have created a workaround for an edge-case in my project, and in my head it should be possible to have it be the default behavior in...

annietllnd

Rewire TensorFlow to rely on tf_keras target.

copybara-service[bot]

float16 quantization runs out of memory for LSTM model

3

No matter the size of the LSTM model, converting it with float16 optimization runs out of memory. **Code to reproduce the issue** [The code snippet to reproduce the issue on...

AminHasanpour

'Pruning in Keras' Example: Unable to fine-tune pruned model on GPU (TF 2.9.2)

5

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...

swapnilsayansaha