We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Traceback (most recent call last): File "/code/infer_api.py", line 10, in infer_api = INFER_API() File "/code/main_infer.py", line 76, in new cls._instance.initialize() File "/code/main_infer.py", line 89, in initialize self.model = load_model('all', 2) TypeError: load_model() missing 1 required positional argument: 'use_sync_bn'
The text was updated successfully, but these errors were encountered:
self.model = load_model('all', 2) 修改为 self.model = load_model('all', 2, use_sync_bn=False) 能运行,但不知是否合理
Sorry, something went wrong.
实在抱歉,use_sync_bn这个参数是为了解决另一个issue提出的在单卡环境下训练RepLKNet时出现的问题而加上去的。这个参数只作用于RepLKNet的训练,并不会对推理产生影响,所以您这么设置是合理的。十分感谢您的issue,后续会解决这个bug,对您在使用上造成的困扰深表歉意。如仍有问题,欢迎随时提出issue。
No branches or pull requests
Traceback (most recent call last):
File "/code/infer_api.py", line 10, in
infer_api = INFER_API()
File "/code/main_infer.py", line 76, in new
cls._instance.initialize()
File "/code/main_infer.py", line 89, in initialize
self.model = load_model('all', 2)
TypeError: load_model() missing 1 required positional argument: 'use_sync_bn'
The text was updated successfully, but these errors were encountered: