model-optimization

model-optimization copied to clipboard

Internal change

copybara-service[bot]

Non-uniform sparsity layer-wise with PolynomialDecay scheduler

2

**System information** - TensorFlow version (you are using): 2.9.1 - Are you willing to contribute it (Yes/No): Yes **Motivation** Instead of assuming that the initial and final sparsity are uniform...

AmoghDabholkar

Input and resource quantization

1

**System information** - TensorFlow version (you are using): tensorflow 2.9.1 - Are you willing to contribute it (Yes/No): No **Motivation** The input and resource need interface for customer layer quantization,...

Jwy-Leo

bilinear upsampling layer cannot be 8-bit quantized correctly

3

**Describe the bug** Hello, I want to do full 8-bit quantization(input, weight all 8-bit) to the network with a bilinear upsampling layer. The fake QAT result in validation set is...

touristourist

QAT for subclass inside the subclass

2

I have one subclass A, which contains another subclass B inside it. I find subclass B in fact didn't get quanted. class A (): self.layers=[] self.layers.append(Dense) self.layers.append(class B) class A_quant(A):...

t7hua

Post-training integer quantization for SSDMobileNet - poor detection accuracy

7

Hi there **Describe the bug** I used [Convert TF Object Detection API model to TFLite](https://colab.research.google.com/github/tensorflow/models/blob/master/research/object_detection/colab_tutorials/convert_odt_model_to_TFLite.ipynb) and tried to modify it, so it is fully int 8 quantized. [Here](https://colab.research.google.com/drive/1XuWniYM6q_0Uffp6SqSC5GUoS4Bd78RM?usp=sharing) is my...

Garstig

Support for nested `tf.keras.layers.Layer`

5

**System information** - `Ubuntu 16.04` - TensorFlow version (you are using): Tried both `2.3.0` and `tf-nightly`(`==2.5.0-dev20210223`) - Are you willing to contribute it (Yes/No): I have tried, but to no...

yycho0108

about the Quantize layer when trans model

2

I have two model, which is mobilenetv1 for classification. the first model, it's download from google: https://storage.googleapis.com/download.tensorflow.org/models/tflite/mobilenet_v1_224_android_quant_2017_11_08.zip the second model, it's ctreat by myself, I make its layers same to...

lzcchl

QAT model saving bug : KeyError: '__inference_depthwise_conv2d_layer_call_fn_126

19

**Describe the bug** Please download the scripts to reproduce from : https://drive.google.com/drive/folders/15cajAZ9sAZ2Uyix8sDVSYku6QCqDCec7?usp=sharing Command to run : python sample_qat.py. I have a simple model with input layer and a depthwise conv2d...

peri044

QAT model saving bug: Unable to save function b'__inference_separable_conv2d_layer_call_fn_961'

15

**Describe the bug** I have a simple model with input layer and a `SeparableConv2D` layer (note that this issue also happens with `Conv2DTranspose`). I'm quantizing this model by adding `quantize_and_dequantize_v2`...

gcunhase