Qi Han

Results 4 issues of Qi Han

env: ubuntau 20.04, pytorch==1.11.0, cuda_version=10.2 error logs: Traceback (most recent call last): File "setup.py", line 12, in cmdclass={'build_ext': BuildExtension}) File "/home/hanqi/miniconda3/envs/glom/lib/python3.7/site-packages/setuptools/__init__.py", line 87, in setup return distutils.core.setup(**attrs) File "/home/hanqi/miniconda3/envs/glom/lib/python3.7/site-packages/setuptools/_distutils/core.py", line...

It seems that MHSA only has one head in the released code. But in the paper, 4 heads are used in MHSA. Is it a simplification for CIFAR dataset?

The code includes some scripts on VOC dataset. However, there is no VOC-related training schemes inside the code. Could someone kindly provide training details (or code) on the VOC dataset?...

How to change your code to run with pytorch1.0? Thank you!