Issues
- 0
The Little Daisy Bake Shop - New Website
#34 opened by madelinedefrank - 1
VQA: Understanding how the model provides us an answer? Need of answer list?
#24 opened by fizahkhalid - 1
Dear Author,Is there any inference code for image retrieval?How can I use this project to inference on my own image-text pairs.
#27 opened by wildwolff - 0
An error in the `Retrieval.py`
#33 opened by jiajinuiuc - 0
The torch version out of date
#32 opened by Hoang-it - 1
About training data
#30 opened by 1049451037 - 0
- 0
Loading frompretrained warnining
#29 opened by lezhang7 - 0
Where is the pretrained model's config file?
#28 opened by lezhang7 - 1
apply an entire BERT as text encoder
#26 opened by lxianl455 - 1
VQA: Limitations in questions and answers
#25 opened by fizahkhalid - 1
Drawing Attention Heatmap
#11 opened by TheodorPatrickZ - 2
Code for Grad-CAM visualization
#23 opened by qiaomu-miao - 4
Script to generate RegionTextJsonDataset?
#13 opened by daizuozhuo - 1
About swin_B_480
#16 opened by Sxx1995 - 2
Fine-tune on VQA
#17 opened by darwann - 1
Performance of different vision encoders
#18 opened by AI-in-Health - 1
About batch sampling `iter_perc`
#19 opened by yangbang18 - 1
NLVR Pretrain
#21 opened by lonestar234028 - 0
- 1
Finetuning On NLVR2
#20 opened by lonestar234028 - 0
- 0
- 2
Training log for the pretrain stage
#12 opened by tgxs002 - 1
- 1
pretrain-base-4m for the X_VLM
#9 opened by wfx0330 - 1
Fine-tuning
#10 opened by TheodorPatrickZ - 2
About license
#8 opened by WangWenhao0716 - 2
Distributed mode for single GPU
#7 opened by TheodorPatrickZ - 6
Hello, please ask the train_files in configs/yaml file to "hdfs: // path / to / vg" error, please change how to set up
#3 opened by zhanghehe8 - 0
Custom image inference
#5 opened by SangMyeongWoh - 1
Hi, could you provide the specific commands of finetuning on coco captioning? Thanks!
#4 opened by yaolinli - 5
- 1