Robinxin123

[email protected]

Germany student

Results 7 comments of


                                            Robinxin123

how to solve this problem ?Traceback (most recent call last): File "tools/train.py", line 287, in <module> main() File "tools/train.py", line 229, in main model.module.load_state_dict(checkpoint['state_dict']) File "/home/wrc/anaconda3/envs/HRNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 539, in getattr type(self).name, name)) AttributeError: 'FullModel' object has no attribute 'module'

> 它是多卡默认，但是你是单卡在跑，所以报错了 It is multi-card default, but you are running with a single card, so an error is reported 大佬，我只有一张卡，要怎么修改知道吗

how to solve this problem ?Traceback (most recent call last): File "tools/train.py", line 287, in <module> main() File "tools/train.py", line 229, in main model.module.load_state_dict(checkpoint['state_dict']) File "/home/wrc/anaconda3/envs/HRNet/lib/python3.6/site-packages/torch/nn/modules/module.py", line 539, in getattr type(self).name, name)) AttributeError: 'FullModel' object has no attribute 'module'

> have you solved the problem? I met the same trouble have you solved the problem?

RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.

> Please turn off distributed training in train.py and do not use syncBN. do u know how to turn off distributed training in train.py? many thanks

choose Only Testing , but still train data

@sxzy 大佬，新手小白问个问题，这里根本就没有testing set，只有train 和validation ,我们怎么test

关于视频数据的预处理

我没看错的话，在two stream network这篇paper里面有提到，光流数据的采样率是10，然后是bi-directional

博主你好，GitHub上公布预训练模型无法下载，能不能发我邮箱一份[email protected]

大佬们，能不能也发我一份，邮箱: [email protected] 非常感谢

graph.channel_dims这个函数有什么作用？

@wolfworld6 ，大佬，解决了吗