Introduction
This repository is the official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.
Data-free Knowledge Distillation for Object Detection
Akshay Chawla, Hongxu Yin, Pavlo Molchanov and Jose Alvarez
NVIDIA
Abstract: We present DeepInversion for Object Detection (DIODE) to enable data-free knowledge distillation for neural networks trained on the object detection task. From a data-free perspective, DIODE synthesizes images given only an off-the-shelf pre-trained detection network and without any prior domain knowledge, generator network, or pre-computed activations. DIODE relies on two key components—first, an extensive set of differentiable augmentations to improve image fidelity and distillation effectiveness. Second, a novel automated bounding box and category sampling scheme for image synthesis enabling generating a large number of images with a diverse set of spatial and category objects. The resulting images enable data-free knowledge distillation from a teacher to a student detector, initialized from scratch. In an extensive set of experiments, we demonstrate that DIODE’s ability to match the original training distribution consistently enables more effective knowledge distillation than out-of-distribution proxy datasets, which unavoidably occur in a data-free setup given the absence of the original domain knowledge.
LICENSE
Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
This work is made available under the Nvidia Source Code License (1-Way Commercial). To view a copy of this license, visit https://github.com/NVlabs/DIODE/blob/master/LICENSE
Setup environment
Install conda [link] python package manager then install the lpr environment and other packages as follows:
$ conda env create -f ./docker_environment/lpr_env.yml
$ conda activate lpr
$ conda install -y -c conda-forge opencv
$ conda install -y tqdm
$ git clone https://github.com/NVIDIA/apex
$ cd apex
$ pip install -v --no-cache-dir ./
Note: You may also generate a docker image based on provided Dockerfile docker_environments/Dockerfile.
How to run?
This repository allows for generating location and category conditioned images from an off-the-shelf Yolo-V3 object detection model.
- Download the directory DIODE_data from google cloud storage: gcs-link (234 GB)
- Copy pre-trained yolo-v3 checkpoint and pickle files as follows:
$ cp /path/to/DIODE_data/pretrained/names.pkl /pathto/lpr_deep_inversion/models/yolo/ $ cp /path/to/DIODE_data/pretrained/colors.pkl /pathto/lpr_deep_inversion/models/yolo/ $ cp /path/to/DIODE_data/pretrained/yolov3-tiny.pt /pathto/lpr_deep_inversion/models/yolo/ $ cp /path/to/DIODE_data/pretrained/yolov3-spp-ultralytics.pt /pathto/lpr_deep_inversion/models/yolo/ - Extract the one-box dataset (single object per image) as follows:
$ cd /path/to/DIODE_data $ tar xzf onebox/onebox.tgz -C /tmp - Confirm the folder
/tmp/oneboxcontaining the onebox dataset is present and has following directories and text filemanifest.txt:$ cd /tmp/onebox $ ls images labels manifest.txt - Generate images from yolo-v3:
$ cd /path/to/lpr_deep_inversion $ chmod +x scripts/runner_yolo_multiscale.sh $ scripts/runner_yolo_multiscale.sh
Notes:
- For ngc, use the provided bash script
scripts/diode_ngc_interactivejob.shto start an interactive ngc job with environment setup, code and data setup. - To generate large dataset use bash script
scripts/LINE_looped_runner_yolo.sh. - Check
knowledge_distillationsubfolder for code for knowledge distillation using generated datasets.
Citation
@inproceedings{chawla2021diode,
title = {Data-free Knowledge Distillation for Object Detection},
author = {Chawla, Akshay and Yin, Hongxu and Molchanov, Pavlo and Alvarez, Jose M.},
booktitle = {The IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
month = January,
year = {2021}
}
147 Dec 3, 2022
156 Dec 28, 2022
47 Nov 17, 2022
75 Dec 28, 2022
80 Dec 16, 2022
9 Nov 14, 2022
9 Sep 26, 2022
19 Jun 7, 2022
37 Nov 10, 2022
112 Dec 2, 2022
180 Dec 19, 2022
129 Dec 24, 2022
6 Nov 21, 2022
13 Dec 10, 2022
97 Dec 13, 2022
443 Dec 6, 2022
274 Dec 26, 2022
75 Dec 22, 2022
215 Dec 19, 2022