Linxi

icon indicating an email [email protected]

icon company alibaba icon location hangzhou icon location Deep Learning, Computer Vision, Large Language Model. Huawei Noah researcher.

Results 4 comments of Linxi

icdar2015结果与论文相差两个点

应该是Deformable CNN的原因

Load pretrained weight error

Hi, I also meet this error. I should use FlamingoForConditionalGeneration load OTTER-LLaMA7B-Init model instead of OtterForConditionalGeneration? And which is the best model which of size if smaller 10B.

What is the ground truth for training?

We use COCO label to generate foreground and background label. Pytorch code is avaliable in https://github.com/IDEA-Research/detrex/blob/main/projects/focus_detr/modeling/two_stage_criterion.py

What is the ground truth for training?

"Multi-category score predictor " is similar to topk token selector in the Encoder of DINO.