Skip to content

Latest commit

 

History

History
138 lines (94 loc) · 4.77 KB

README.MD

File metadata and controls

138 lines (94 loc) · 4.77 KB
Raw

CompressAI-Vision-logo

CompressAI-Vision helps you to develop, test and evaluate compression models with standardized tests in the context of compression methods optimized for machine tasks algorithms such as Neural-Network (NN)-based detectors.

It currently focuses on two types of pipeline:

  • Video compression for remote inference (compressai-remote-inference), which corresponds to the MPEG "Video Coding for Machines" (VCM) activity.

  • Split inference (compressai-split-inference), which includes an evaluation framework for compressing intermediate features produced in the context of split models. The software supports all thepipelines considered in the related MPEG activity: "Feature Compression for Machines" (FCM).

CompressAI-Vision supported pipelines

Features

  • Detectron2 is used for object detection (Faster-RCNN) and instance segmentation (Mask-RCNN)

  • JDE is used for Object Tracking

Documentation

A complete documentation is provided here, including installation, CLI usage, as well as tutorials.

installation

initialization of the environment

To get started locally and install the development version of CompressAI-Vision, first create a virtual environment with python==3.8:

python3.8 -m venv venv
source ./venv/bin/activate
pip install -U pip

The CompressAI library providing learned compresion modules is available as a submodule. It can be initilized by running:

git submodule update --init --recursive

Note: the installation script documented below installs compressai from source expects the submodule to be populated.

installation of compressai-vision and supported vision models:

First, if you want to manually export CUDA related paths, please source (e.g. for CUDA 11.8):

bash scripts/env_cuda.sh 11.8

Then, run:, please run:

bash scripts/install.sh

For more otions, check:

bash scripts/install.sh --help

NOTE 1: install.sh gives you the possibility to install vision models' source and weights at specified locations so that mutliple versions of compressai-vision can point to the same installed vision models

NOTE 2: the downlading of JDE pretrained weights might fail. Check that the size of following file is ~558MB. path/to/weights/jde/jde.1088x608.uncertainty.pt The file can be downloaded at the following link (in place of the above file path): "https://docs.google.com/uc?export=download&id=1nlnuYfGNuHWZztQHXwVZSL_FvfE551pA"

Usage

Split inference pipelines

To run split-inference pipelines, please use the following command:

compressai-split-inference --help

Note that the following entry point is kept for backward compability. It runs split inference as well.

compressai-vision-eval --help

For example for testing a full split inference pipelines without any compression, run

compressai-vision-eval --config-name=eval_split_inference_example

Remote inference pipelines

For remote inference (MPEG VCM-like) pipelines, please run:

compressai-remote-inference --help

Configurations

Please check other configuration examples provided in ./cfgs as well as examplary scripts in ./scripts

Test data related to the MPEG FCM activity can be found in ./data/mpeg-fcm/

For developers

After your dev, you can run (and adapt) test scripts from the scripts/tests directory. Please check scripts/tests/Readme.md for more details

Contributing

Code is formatted using black and isort. To format code, type:

make code-format

Static checks with those same code formatters can be run manually with:

make static-analysis

Compiling documentation

To produce the html documentation, from docs/, run:

make html

To check the pages locally, open docs/_build/html/index.html

License

CompressAI-Vision is licensed under the BSD 3-Clause Clear License

Authors

Fabien Racapé, Hyomin Choi, Eimran Eimon, Sampsa Riikonen, Jacky Yat-Hong Lam

Related links