datar001
datar001
Thanks for your reply. Is it right about "the gradient accumulation and all tags in one iteration"?   And '20k for 6 tags' is the typo? The official repo...
> Hi, please make sure you have successfully installed the following two libs: > > block==0.0.5 > block.bootstrap.pytorch==0.1.6
I have installed these libs:  And I install all libs according to the requirements.txt.
The environment was achieved by the guidance in this repo. It seems to be right. python 3.6.8, torch1.6.0 I test this line in the python console and it also outputs...
I have solved this problem just now. It seems to be caused by pip resource. When I re-install block and block.bootstrap.pytorch from mirrors.aliyun.com/pypi/simple rather than pypi.tuna.tsinghua.edu.cn/simple, this code runs well.
请问有支持中文提示词的版本发布吗
Thanks!
I have the same question, Why is dim=0 not the dim =1? a better performance?
wow, maybe i am a blind man.... And, If the dim=-2 rather than -1 in Line 45 in networks/VQAModel/HGA.py, the performance will get a small improvement. This seems an implement...
I find that this problem does not hinder running codes. It can be able to train and evaluate the project. However, there are two additional minor errors in Line 51...