You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I want to train in KITTI, but it's wrong with AssertionError like this: 2024-12-13 08:05:11,169 INFO [helpers.py:188] Loading pretrained weights from url (https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/mobilenetv2_100_ra-b33bc2c4.pth) Parameter Count: 12598114 Traceback (most recent call last): File "train_stereo.py", line 239, in <module> train(args) File "train_stereo.py", line 124, in train train_loader = datasets.fetch_dataloader(args) File "/home/IGEV-main/IGEV-Stereo/core/stereo_datasets.py", line 312, in fetch_dataloader new_dataset = KITTI(aug_params) File "/home/IGEV-main/IGEV-Stereo/core/stereo_datasets.py", line 252, in __init__ assert os.path.exists(root) AssertionError
I dont know how this mistake happen
The text was updated successfully, but these errors were encountered:
Thank you! I revisited the path based on your prompt and I noticed that the case of the dataset folder is not uniform, which is what is causing this issue.
I want to train in KITTI, but it's wrong with AssertionError like this:
2024-12-13 08:05:11,169 INFO [helpers.py:188] Loading pretrained weights from url (https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/mobilenetv2_100_ra-b33bc2c4.pth) Parameter Count: 12598114 Traceback (most recent call last): File "train_stereo.py", line 239, in <module> train(args) File "train_stereo.py", line 124, in train train_loader = datasets.fetch_dataloader(args) File "/home/IGEV-main/IGEV-Stereo/core/stereo_datasets.py", line 312, in fetch_dataloader new_dataset = KITTI(aug_params) File "/home/IGEV-main/IGEV-Stereo/core/stereo_datasets.py", line 252, in __init__ assert os.path.exists(root) AssertionError
I dont know how this mistake happen
The text was updated successfully, but these errors were encountered: