Issues
- 1
- 0
Download link invalid
#174 opened by kochsebastian - 2
Where can I get Cap4M?
#126 opened by zetaodu - 0
Creating a Dockerfile for GLIP
#173 opened by Meiye-lj - 2
- 1
About Object365 dataset
#161 opened by YangJae96 - 1
- 1
Demo Error Problem
#171 opened by Bowie1026 - 3
Huggingface Demo Error
#165 opened by wuyefa - 1
The loss is zero all the time, when I fine turning myself datasets, which coco format
#170 opened by TfeiSong - 5
Release of GLIP V2
#136 opened by AmrinKareem - 3
The link of annotation for Objects365 cannot be opened :https://penzhanwu2bbs.blob.core.windows.net/data/GLIPv1_Open/Objects365/objects365_train_vgoiv6.cas2000.yaml
#155 opened by yeppp27 - 1
COCO Fine-Tuning
#169 opened by fengjianhui158 - 0
forward error:rpn vldyhead
#168 opened by Thaumaturge2020 - 1
- 0
ModuleNotFoundError: No module named 'maskrcnn_benchmark.modeling.roi_heads.keypoint_head'
#167 opened by DiDi96-87 - 0
About BiMultiHeadAttention
#166 opened by kanuore - 0
- 0
Not able to download the lvis annotations
#160 opened by jsleeo424 - 0
cc3m dataset
#158 opened by lv-0413 - 2
- 1
Minimal hardware dependency of finetune.
#157 opened by Ethantequila - 2
Running on CPU
#141 opened by vatdut8994 - 1
About Custom Dataset Evaluation
#143 opened by zzhujiuxingc - 0
Calculate the parameters and FLOPs
#153 opened by Qia98 - 0
Can not get weight files
#152 opened by KM-github-source - 0
Zero-shot result of GLIPv2 on phrasecut
#151 opened by 594zyc - 4
Cannot access to pre-trained backbone checkpoints
#148 opened by WeichenZh - 0
- 0
Some confusion about the results of fixed ap?
#150 opened by kuiran - 2
the docker doesn't support 4090 GPU
#144 opened by whhong5 - 1
Required version for transformer
#147 opened by Nana2929 - 2
Query about word-region alignment score
#135 opened by tfc-0 - 3
- 2
question about the predict_demo
#128 opened by william1111111111 - 1
Does GLIP support keypoint detection
#146 opened by ybk66 - 1
An error is reported test_net.py running
#124 opened by hymhhh - 0
when input classes exceeds token length
#142 opened by vishalvijay99 - 1
- 1
- 0
- 0
batch captioning
#138 opened by tfc-0 - 0
Question about fintune on odinw dataset config file
#137 opened by ws1hope - 0
How to finetune on single GPU
#134 opened by ws1hope - 0
How to finetune on single GPU
#133 opened by ws1hope - 0
How to run my own dataset
#132 opened by small-code-cat - 0
Cannot get these files
#131 opened by zeyunZhao - 0
We cannot get the tsv files for pretrain?
#130 opened by zetaodu - 0
论文问题
#129 opened by Zesheng666 - 0