Skip to content

Latest commit

 

History

History
53 lines (46 loc) · 1.8 KB

README.md

File metadata and controls

53 lines (46 loc) · 1.8 KB
Raw

tf_example6 example

Step-by-Step

This example is used to demonstrate how to use default user-facing APIs to quantize a model.

Prerequisite

1. Installation

pip install -r requirements.txt

2. Prepare Dataset

TensorFlow models repo provides scripts and instructions to download, process and convert the ImageNet dataset to the TF records format. We also prepared related scripts in TF image_recognition example.

3. Download the FP32 model

wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_6/mobilenet_v1_1.0_224_frozen.pb

Run

1. Run Command

  • Run quantization
python test.py --tune --dataset_location=/path/to/imagenet/
  • Run benchmark, please make sure benchmark the model should after tuning.
python test.py --benchmark --dataset_location=/path/to/imagenet/

2. Introduction

  • We only need to add the following lines for quantization to create an int8 model.
    quantized_model = fit(
        model="./mobilenet_v1_1.0_224_frozen.pb",
        conf=config,
        calib_dataloader=calib_dataloader,
        eval_dataloader=eval_dataloader)
    tf.io.write_graph(graph_or_graph_def=quantized_model.model,
                        logdir='./',
                        name='int8.pb',
                        as_text=False)
  • Run benchmark, use self defined eval_func to test accuracy and performance.
     # Optional, run benchmark 
    from neural_compressor.model import Model
    evaluate(Model('./int8.pb'))