Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
root d1fa44e40e | 11 months ago | |
---|---|---|
.ipynb_checkpoints | 11 months ago | |
config | 1 year ago | |
launchers | 1 year ago | |
pth | 1 year ago | |
resources | 1 year ago | |
scripts | 1 year ago | |
visualDet3D | 11 months ago | |
=8.3.2 | 11 months ago | |
DATA.md | 1 year ago | |
INSTALL.md | 1 year ago | |
LICENSE | 1 year ago | |
README.md | 1 year ago | |
make.sh | 1 year ago | |
requirement.txt | 1 year ago | |
run.py | 11 months ago | |
run1.py | 11 months ago | |
run2.py | 11 months ago | |
run3.py | 11 months ago | |
test.sh | 11 months ago |
MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer (CVPR 2022) [paper]
Kuan-Chih Huang, Tsung-Han Wu, Hung-Ting Su, Winston H. Hsu.
Please refer to INSTALL.md for installation and to DATA.md for data preparation.
Move to root and train the network with $EXP_NAME
:
cd #MonoDTR_ROOT
./launcher/train.sh config/config.py 0 $EXP_NAME
Note: this repo only supports single GPU training. Also, the training randomness for monocular 3D object detection may cause the variance of ±1 AP3D.
To evaluate on the validation set using checkpoint $CHECKPOINT_PATH
:
./launcher/eval.sh config/config.py 0 $CHECKPOINT_PATH validation
We provide a good checkpoint for the car category on train/val split here.
If you find our work useful in your research, please consider citing:
@inproceedings{huang2022monodtr,
author = {Kuan-Chih Huang and Tsung-Han Wu and Hung-Ting Su and Winston H. Hsu},
title = {MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer},
booktitle = {CVPR},
year = {2022}
}
Our codes are mainly based on visualDet3D, and also benefits from CaDDN, MonoDLE, and LoFTR. Thanks for their contributions!
This project is released under the MIT License.
No Description
Python Text Cuda C++ Makefile other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》