Linxi

[email protected]

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

Results 13 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.

Datasets conversion tool

Can you provide icdar2015 dataset conversion script, thanks

Datasets conversion tool

> Thanks a lot, but now I still can not find converision scripts.

Data to evaluate Video Detailed Description.

I have no access to it also, can you provide public url.

Video Detailed Description data cannot access if MS account is not from mbzuai

Still can not access it.

关于包

This repo only upload changed files. detrex have add Focus-DETR to their repo, https://github.com/IDEA-Research/detrex/tree/main/projects/focus_detr

AttributeError: 'LlavaQwenConfig' object has no attribute 'mm_newline_position'

how you solve this problem.

1
2
›