This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).
MIT License
382
stars
88
forks
source link
ImportError: cannot import name 'Di1stributedDataParallel' from 'apex.parallel' #22
The paltform is window10, and there is only one GPU=RTX GeForce 3080
pytorch version==1.7.1,
tensorboard version ==1.15.0,
apex version==0.1
Q: Every time when i tried to train with the command "train.py --dataset CUB_200_2011 --split overlap --num_steps 10000 --fp16 --name sample_run", it always gave me a error feedback, like "ImportError: cannot import name 'Di1stributedDataParallel' from 'apex.parallel' "
Any guy know what is the reason causing this error? If you know some likely reasons, please tell me, thank you so much. God bless you!
The paltform is window10, and there is only one GPU=RTX GeForce 3080 pytorch version==1.7.1, tensorboard version ==1.15.0, apex version==0.1 Q: Every time when i tried to train with the command "train.py --dataset CUB_200_2011 --split overlap --num_steps 10000 --fp16 --name sample_run", it always gave me a error feedback, like "ImportError: cannot import name 'Di1stributedDataParallel' from 'apex.parallel' " Any guy know what is the reason causing this error? If you know some likely reasons, please tell me, thank you so much. God bless you!