model-optimization

model-optimization copied to clipboard

quantization.keras.quantize_model function runtime error with mobilenet v3

6

**Describe the bug** tensorflow_model_optimization.quantization.keras.quantize_model function throws the following error with mobilenet v3. ``` Traceback (most recent call last): File "issue_report.py", line 14, in q_aware_model = tfmo.quantization.keras.quantize_model(model_mv3) File "/home/.local/lib/python3.8/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py", line 137,...

ejcgt

Add MbyN sparsity schedulers

5

This PR introduce two new schedulers for M_by_N sparsity   - PolynomialDecayMbyNSparsity   - ConstantMbyNSparsity #### [ConstantMbyNSparsity](https://github.com/tensorflow/model-optimization/pull/855/files#diff-15df3b8c3fdb2a06997a17f8c698e97b2e5533f85822bcba244be45b7d92f8bdR262-R277) Pruning model at step `prune_step`, that is,  m_by_n sparsity masks calculate only at `prune_step` then...

psunn

Set zero_debias=True for Quantization Aware Training

3

Hi, I see that TF version 1's QAT library uses **zero_debias** as True. However, the TFMOT's quantization library calls the following in the quant_ops.py: _assign_min = moving_averages.assign_moving_average( min_var, range_min, ema_decay,...

smohan10

[RNN] Stateful LSTM can't be converted to TF Lite with Integer Quantization

21

### 1. System information - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): **Windows 10** - TensorFlow installation (pip package or built from source): **pip package** - TensorFlow library (version,...

AnastGerus

Weight in fully connected layers don't follow tensorflow quantization spec (zero-point!=0)

3

### 1. System information - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04.5 LTS - TensorFlow installation (pip package or built from source): pip - TensorFlow library (version,...

bhbruce

Remove experimental modules from top level API

copybara-service[bot]

Activity Regularizer not working with quantization aware training (QAT)

1

**Describe the bug** Activity Regularizer not working with quantization aware training (QAT). On further evaluation I also saw that it creates a tensor of type `` for Actvity regularization loss...

bayesian-mind

pruning example code for GNMT

1

**System information** - TensorFlow version (you are using): 2.5.0 - Are you willing to contribute it (Yes/No): Yes **Motivation** There is pruning result of GNMT EN-DE and GNMT DE-EN on...

TaeheeJeong

problem with quantizing the BN layer

6

Hello, I am trying to perform a QAT on a ResNet50 network with BN layers, and I keep getting the following error: ``` ValueError: Shape must be rank 4 but...

lovodkin93

QAT for object detection models?

4

**System information** - TensorFlow version (you are using):2.6 - Are you willing to contribute it (Yes/No): **Motivation** Need to run OD models on device, after QAT. **Describe the feature** Currently...

tensorbuffer