-
Thanks for your contribution, when using lvis db, there is "lvis_sample_areas.pickle" required, could you please share the file with me or share an example data structure of this file?
Thanks in adva…
-
使用的命令是：
python image_demo.py configs/pretrain/yolo_world_s_dual_vlpan_l2norm_2e-3_100e_4x8gpus_obj365v1_goldg_train_lvis_minival.py models/yolo_world_seg_m_dual_vlpan_2e-4_80e_8gpus_allmodules_finetu…
-
Thank you for sharing your excellent work. I trained a project using detectron2 as backbone. But when I trained a model in a machine with 8 GPUs, I met OSError: [Errno 113] No route to host as follow:…
-
Thanks for open source and I enjoyed reading your paper. A few questions about training set
- Could you share your training set object list? (I found several jsons in this repo but am unsure which …
-
great work!
how to use MixedGroundingDataset to load CC3M pretrain data, the CC3M image-text data annotations doesn't has 'tokens_positive' as MixedGroundingDataset defined, if I want to use CC3M b…
-
Hi
I used a custom dataset on this project, which has great result in the fine tune step( eval result was great ) , but when I try to use the demo to detect the image, it does not detect anything, wh…
-
## Instructions To Reproduce the 🐛 Bug:
1. Full runnable code or full changes made:
```
# I want to have detectron2 to be able to use layoutparser.
# On the webpage (https://layout-parser.github.…
-
Hello author，
Thank you very much for the dataset you provided, which will be of great help to my future research work. Here I have two questions to ask you，hope to get your reply：
What is the relat…
-
Hello,
Thank you for the exciting work and code release!
It seems that eval_lvis requests conv_temp='groma', but conversation.py does not have a 'groma' conv_templates. Which template should we…
-
Thanks for your inspiring work!
It seems that some file is missing: 'datasets/coco/zero-shot/instances_train2017_seen_2_del_cat_info.json' at https://github.com/clin1223/VLDet/blob/c3b9bc52205cd1…