Seems that your code isn't complied with numpy>=1.20

[ganchi-huanggua]

Project file: Dassl.pytorch/dassl/data/transforms/randaugment.py, line 93 in SolarizeAdd, np.int is deprecated in NumPy 1.20. But now almost every pytorch version requires NumPy>=1.24, including pytorch 1.8.1. Maybe I made a mistake but still please check it out. I'd appreciate it.

Original traceback:

File "/home/.../code/Dassl.pytorch/dassl/data/transforms/randaugment.py", line 93, in SolarizeAdd
img_np = np.array(img).astype(np.int)
File "/home/.../.conda/envs/usb/lib/python3.8/site-packages/numpy/init.py", line 305, in getattr
raise AttributeError(former_attrs[attr])
AttributeError: module 'numpy' has no attribute 'int'.
np.int was a deprecated alias for the builtin int. To avoid this error in existing code, use int by itself. Doing this will not modify any behavior and is safe. When replacing np.int, you may wish to use e.g. np.int64 or np.int32 to specify the precision. If you wish to review your current use, check the release note link for additional information.
The aliases was originally deprecated in NumPy 1.20; for more details and guidance see the original release note at:
https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations