Wayne Mao
Wayne Mao
I also encountered the same bug. Thank you.
是的，刚刚clone的代码 看着像这里出错： ``` response = openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=messages, ) ```
嗯嗯，确实是账户的问题，简单加个报错就行
I'm so sorry for the late response. Recently, I've been busy with my doctoral thesis. Sure, the pretrained weights include a convolution with a 7x7 kernel. If you need the...
More specifically, the image weights are pretrained on ImageNet-1k. https://github.com/open-mmlab/mmpretrain/tree/master/configs/convnext
I'm so sorry for the late response. Recently, I've been busy with my doctoral thesis. I will gradually update my code over the next 2 months.
We follow the pillar encoder, we do not use dynamic encoding.