Skip to content

Latest commit

 

History

History
executable file
·
38 lines (35 loc) · 1.4 KB

README.md

File metadata and controls

executable file
·
38 lines (35 loc) · 1.4 KB

Dawnbench Inference on Imagenet

Summary

The inference speed of ResNet26-based model is improved through PAI-Blade. PAI-Blade is the framework for high-efficiency model deployment developed by AliCloud PAI: PAI-Blade. The BBS (Blade Benchmark Suite) can be accessed: BBS. In addition, optimized INT8 conv2d operators are generated through TVM TensorCore AutoCodeGen.

Run inference

  1. Clone this repo.
  2. Put Imagenet validation set (50000 images) in imagenet/val_data/.
./imagenet/val_data/
├── ILSVRC2012_val_00000001.JPEG
├── ILSVRC2012_val_00000002.JPEG
├── ILSVRC2012_val_00000003.JPEG
├── ILSVRC2012_val_00000004.JPEG
├── ILSVRC2012_val_00000005.JPEG
├── ILSVRC2012_val_00000006.JPEG
...
  1. Pull nvcr.io/nvidia/tensorrt:19.09-py3 from NGC.
  2. Start nvcr.io/nvidia/tensorrt:19.09-py3 container, and install dependencies:
# start docker container
sh run.sh

# Install TensorFlow
pip install tensorflow==1.13.1
  1. Set environment in host:
sh set_env.sh
  1. In the container workspace, run cmd as below:
# Assuming the workspace is mounted as /app
cd /app

# Run for inference
sh eval.sh