The train.py successfully runs. The problem appears when I try to run the test_disp.py. To be more precise, I checked the test_files_eigen.txt and the samples that are inside that file, dont exist and also have a different path format than the one in extracted KITTI data.
Thats the output of the prepare_train_data.py script.
and thats the content of the test_files_eigen.txt
As you can see the structure differs a lot.
Also, the drives for each date in test_files_eigen.txt dont exist in the extracted KITTI data.
In extention of my question, I saw that in kitti_raw_loader you create a txt file named test_scenes which contains some dates. Whats the purpose of that file?
Hello Clemenent,
I have set up the data as you descripe in the README. More specifically I run
python3 data/prepare_train_data.py /path/to/raw/kitti/dataset/ --dataset-format 'kitti_raw' --dump-root /path/to/resulting/formatted/data/ --width 416 --height 128 --static-frames /path/to/static_frames.txt --with-depth --with-poseto get the data for KITTI.
The train.py successfully runs. The problem appears when I try to run the test_disp.py. To be more precise, I checked the test_files_eigen.txt and the samples that are inside that file, dont exist and also have a different path format than the one in extracted KITTI data.
Thats the output of the prepare_train_data.py script.
and thats the content of the test_files_eigen.txt
As you can see the structure differs a lot.
Also, the drives for each date in test_files_eigen.txt dont exist in the extracted KITTI data.
In extention of my question, I saw that in kitti_raw_loader you create a txt file named test_scenes which contains some dates. Whats the purpose of that file?