Yuanhao Zou

为什么要用model_train和model一起训练，区别是什么？

1

https://github.com/bubbliiiing/unet-pytorch/blob/b3ed98897d823465eae30bd41894b305303ef965/utils/utils_fit.py#L11 这里不是很懂，model传入后只是用来保存权重吗

Simple Question about object detection code

1

https://github.com/doc-doc/CoVGT/blob/cbc9fa7830b304f3c3f9c53040489ea9ad35a9aa/model/EncoderVid.py#L56-L71 Hi, I am reading your code about object detection. I found the above one in your EncoderVid.py Do you still remember why you choose 5 dimension (dim_bbox) for positional...

Hi, thank you for your great works! I am wondering how you analyze the stsg and input it into the sg_encoder as `g` and `h` in https://github.com/scofield7419/Video-of-Thought/blob/4d4fad22a66c025fdd3d0045a364867461cbb88d/motionepic/model/multimodal_encoder/stsg.py#L171 Could you also...