can't untar trained model in your google drive

[3togo]

https://drive.google.com/drive/folders/1H1AFqSS8wr_YzwG2xWwAQHTfXN5Moxmx

tar xvf exp_pose_model_best.pth.tar
tar: exp_pose_model_best.pth.tar: Cannot open: No such file or directory
tar: Error is not recoverable: exiting now

also, how to run test_dis.py?
python3 test_disp.py --dataset-dir misc --pretrained-dispnet checkpoints/trained/dispnet_model_best.pth.tar --output-dir checkpoints/output/

[ClementPinard]

You d'ont have to untar it. the .tar.pth is a convention it took from this pytorch example : https://github.com/pytorch/examples/blob/master/imagenet/main.py#L290

For test_disp.py, by default, the dataset type is KITTI. You have to set the --dataset-dir argument to the root of KITTI raw, and you also have to set the --dataset-list to a list file that will point what images to test. To get the same dataset list as in original paper (and Eigen et al.), you can use the one placed in kitti_eval : https://github.com/ClementPinard/SfmLearner-Pytorch/blob/master/kitti_eval/test_files_eigen.txt