深度估计-基于激光雷达+单目相机的自监督深度估计算法实现-优质项目实战.zip

# self-supervised-depth-completion <p align="center"> <img src="https://j.gifs.com/rRrOW4.gif" alt="photo not available" height="50%"> </p> ## Dependency This code was tested with Python 3 and PyTorch 1.0 on Ubuntu 16.04. ```bash pip install numpy matplotlib Pillow pip install torch torchvision # pytorch # for self-supervised training requires opencv, along with the contrib modules pip install opencv-contrib-python==3.4.2.16 ``` ## Data - Download the [KITTI Depth](http://www.cvlibs.net/datasets/kitti/eval_depth.php?benchmark=depth_completion) Dataset from their website. Use the following scripts to extract corresponding RGB images from the raw dataset. ```bash ./download/rgb_train_downloader.sh ./download/rgb_val_downloader.sh ``` The downloaded rgb files will be stored in the `../data/data_rgb` folder. The overall code, data, and results directory is structured as follows (updated on Oct 1, 2019) ``` . ├── self-supervised-depth-completion ├── data | ├── data_depth_annotated | | ├── train | | ├── val | ├── data_depth_velodyne | | ├── train | | ├── val | ├── depth_selection | | ├── test_depth_completion_anonymous | | ├── test_depth_prediction_anonymous | | ├── val_selection_cropped | └── data_rgb | | ├── train | | ├── val ├── results ``` ## Trained Models Download our trained models at http://datasets.lids.mit.edu/self-supervised-depth-completion to a folder of your choice. - supervised training (i.e., models trained with semi-dense lidar ground truth): http://datasets.lids.mit.edu/self-supervised-depth-completion/supervised/ - self-supervised (i.e., photometric loss + sparse depth loss + smoothness loss): http://datasets.lids.mit.edu/self-supervised-depth-completion/self-supervised/ ## Commands A complete list of training options is available with ```bash python main.py -h ``` For instance, ```bash # train with the KITTI semi-dense annotations, rgbd input, and batch size 1 python main.py --train-mode dense -b 1 --input rgbd # train with the self-supervised framework, not using ground truth python main.py --train-mode sparse+photo # resume previous training python main.py --resume [checkpoint-path] # test the trained model on the val_selection_cropped data python main.py --evaluate [checkpoint-path] --val select ```