WARNING: Your kernel does not support swap limit capabilities or the cgroup is not mounted. Memory limited without swap.
Traceback (most recent call last):
File "/tmp/codalab/tmpy9thti/run/program/evaluate.py", line 107, in
pred_disps = np.load(submit_path, fix_imports=True, encoding='latin1', allow_pickle=True)["data"]
File "/opt/conda/lib/python3.9/site-packages/numpy/lib/npyio.py", line 243, in __getitem__
return format.read_array(bytes,
File "/opt/conda/lib/python3.9/site-packages/numpy/lib/format.py", line 747, in read_array
array = pickle.load(fp, **pickle_kwargs)
ModuleNotFoundError: No module named 'torch'
Is there an abnormality in the backend runtime environment?
Posted by: Suzally @ Feb. 22, 2023, 3:46 p.m.Hi Suzally,
Thanks for your information!
We didn't encounter such an error before. Did you submit the correct compressed .npz file to the server? If so, the backend is purely numpy and should not cause trouble with other libraries. Please follow the same steps as listed on this page: https://github.com/ldkong1205/RoboDepth/tree/main/competition#track-2-fully-supervised-depth-estimation-1.
Please let us know if the above solves your problem. Thanks!
Posted by: LingdongKong @ Feb. 22, 2023, 3:56 p.m.Thank you for your reply. I found out that it was indeed my zip file that was having the problem.
Posted by: Suzally @ Feb. 22, 2023, 4:33 p.m.Hi Suzally,
Glad to hear that you have solved the problem!
Feel free to let us know if you encounter any other problems.
Posted by: LingdongKong @ Feb. 22, 2023, 11:46 p.m.