litemono代码

1.从litemono打包下载litemono

2.下载monodepth2，将splits中的eigen和eigen_zhou下载下来替代litemono里的splits中的内容

3.下载kitti数据集并按照下方格式进行整理放到代码根目录

kitti_data
|
├── 2011_09_26
│   ├── 2011_09_26_drive_0001_sync
│   │   ├── image_00
│   │   ├── image_01
│   │   ├── image_02
│   │   ├── image_03
│   │   ├── oxts
│   │   └── velodyne_points│   
│   ├── ...
│   ├── calib_cam_to_cam.txt
│   ├── calib_imu_to_velo.txt
│   └── calib_velo_to_cam.txt
├── 2011_09_28
│   ├── 2011_09_28_drive_0001_sync
│   │   ├── image_00
│   │   ├── image_01
│   │   ├── image_02
│   │   ├── image_03
│   │   ├── oxts
│   │   └── velodyne_points
│   ├── ...│   
│   ├── calib_cam_to_cam.txt
│   ├── calib_imu_to_velo.txt
│   └── calib_velo_to_cam.txt
├── 2011_09_29
│   ├── 2011_09_29_drive_0004_sync
│   │   ├── image_00
│   │   ├── image_01
│   │   ├── image_02
│   │   ├── image_03
│   │   ├── oxts
│   │   └── velodyne_points
│   ├── ...│   
│   ├── calib_cam_to_cam.txt
│   ├── calib_imu_to_velo.txt
│   └── calib_velo_to_cam.txt
├── 2011_09_30
│   ├── 2011_09_30_drive_0016_sync
│   │   ├── image_00
│   │   ├── image_01
│   │   ├── image_02
│   │   ├── image_03
│   │   ├── oxts
│   │   └── velodyne_points│   
│   ├── ...│  
│   ├── calib_cam_to_cam.txt
│   ├── calib_imu_to_velo.txt
│   └── calib_velo_to_cam.txt
└── 2011_10_03
    ├── 2011_10_03_drive_0027_sync
    │   ├── image_00
    │   ├── image_01
    │   ├── image_02
    │   ├── image_03
    │   ├── oxts
    │   └── velodyne_points
    ├── ...
    ├── calib_cam_to_cam.txt
    ├── calib_imu_to_velo.txt
    └── calib_velo_to_cam.txt

4.创建虚拟环境(litemono/python3.8/pytorch1.11.0/cuda10.2)

5.根据代码中显示红色缺失的包来安装依赖包

通过访问 https://github.com/saadnaeem-dev/pytorch-linear-warmup-cosine-annealing-warm-restarts-weight-decay把这个包下载下来，然后解压后把linear_warmup_cosine_annealing_warm_restarts_weight_decay这个文件夹放到你创建的虚拟环境的site-packages里

6.项目根目录创建pth文件夹，下载resnet预训练模型到pth（这一步没有也可以）

model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-f37072fd.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-b627a593.pth',
    'resnet50': 'https://download.pytorch.org/models/resnet50-0676ba61.pth',
    'resnet101': 'https://download.pytorch.org/models/resnet101-63fe2227.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-394f9c45.pth',
    'resnext50_32x4d': 'https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth',
    'resnext101_32x8d': 'https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth',
    'wide_resnet50_2': 'https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth',
    'wide_resnet101_2': 'https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth',
}

7.下载Imagenet预训练模型到pth当作encoder预训练模型，就是训练命令中的--mypretrain参数

8.修改options里的内容进行参数配置,以及trainer.py的152行要修改成一直使用png格式，Lite-Mono-main/kitti_utils.py中85行把np.int改成int。

9.进行训练

 python train.py --data_path kitti_data --model_name mytrain --mypretrain pth/lite-mono-pretrain.pth

10.进行评估

python evaluate_depth.py --load_weights_folder path/to/your/weights/folder --data_path path/to/kitti_data/ --model lite-mono

11.进行测试

python test_simple.py --load_weights_folder path/to/your/weights/folder --image_path path/to/your/test/image

以上三个命令都可使用--load_weights_folder但是加载的目录里要有六个内容，即"encoder.pth", "depth.pth", "pose_encoder.pth", "pose.pth","adam.pth","adam_pose.pth"