Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
yanqing 5efe2b120a | 1 year ago | |
---|---|---|
datasets | 1 year ago | |
img | 1 year ago | |
networks | 1 year ago | |
splits/eigen | 1 year ago | |
.gitignore | 1 year ago | |
README.md | 1 year ago | |
evaluate_depth.py | 1 year ago | |
kitti_utils.py | 1 year ago | |
layers.py | 1 year ago | |
license | 1 year ago | |
options.py | 1 year ago | |
test_simple.py | 1 year ago | |
train.py | 1 year ago | |
trainer.py | 1 year ago | |
utils.py | 1 year ago |
A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
[paper link]
Ning Zhang*, Francesco Nex, George Vosselman, Norman Kerle
(Lite-Mono-8m 1024x320)
You can download the trained models using the links below.
--model | Params | ImageNet Pretrained | Input size | Abs Rel | Sq Rel | RMSE | RMSE log | delta < 1.25 | delta < 1.25^2 | delta < 1.25^3 |
---|---|---|---|---|---|---|---|---|---|---|
lite-mono | 3.1M | yes | 640x192 | 0.107 | 0.765 | 4.561 | 0.183 | 0.886 | 0.963 | 0.983 |
lite-mono-small | 2.5M | yes | 640x192 | 0.110 | 0.802 | 4.671 | 0.186 | 0.879 | 0.961 | 0.982 |
lite-mono-tiny | 2.2M | yes | 640x192 | 0.110 | 0.837 | 4.710 | 0.187 | 0.880 | 0.960 | 0.982 |
lite-mono-8m | 8.7M | yes | 640x192 | 0.101 | 0.729 | 4.454 | 0.178 | 0.897 | 0.965 | 0.983 |
lite-mono | 3.1M | yes | 1024x320 | 0.102 | 0.746 | 4.444 | 0.179 | 0.896 | 0.965 | 0.983 |
lite-mono-small | 2.5M | yes | 1024x320 | 0.103 | 0.757 | 4.449 | 0.180 | 0.894 | 0.964 | 0.983 |
lite-mono-tiny | 2.2M | yes | 1024x320 | 0.104 | 0.764 | 4.487 | 0.180 | 0.892 | 0.964 | 0.983 |
lite-mono-8m | 8.7M | yes | 1024x320 | 0.097 | 0.710 | 4.309 | 0.174 | 0.905 | 0.967 | 0.984 |
The RoboDepth Challenge Team is evaluating the robustness of different depth estimation algorithms. Lite-Mono has achieved the best robustness to date.
Please refer to Monodepth2 to prepare your KITTI data.
python test_simple.py --load_weights_folder path/to/your/weights/folder --image_path path/to/your/test/image
python evaluate_depth.py --load_weights_folder path/to/your/weights/folder --data_path path/to/kitti_data/ --model lite-mono
pip install 'git+https://github.com/saadnaeem-dev/pytorch-linear-warmup-cosine-annealing-warm-restarts-weight-decay'
python train.py --data_path path/to/your/data --model_name mytrain --num_epochs 30 --batch_size 12 --mypretrain path/to/your/pretrained/weights --lr 0.0001 5e-6 31 0.0001 1e-5 31
tensorboard --log_dir ./tmp/mytrain
@article{zhang2022lite,
title={Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation},
author={Zhang, Ning and Nex, Francesco and Vosselman, George and Kerle, Norman},
journal={arXiv preprint arXiv:2211.13202},
year={2022}
}
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》