FightingFighting

'visual_genome.api' has no attribute 'GetImageIdsInRange'

1

AttributeError: module 'visual_genome.api' has no attribute 'GetImageIdsInRange'

AttributeError: 'DetectFeatLmdb' object has no attribute 'env'

5

when I run python train_re.py --config config/train-refcoco-base-1gpu.json --output_dir $RE_EXP I just get this result. 03/11/2021 11:44:06 - INFO - __main__ - Loading Train Dataset /txt_db/refcoco_train.db, /img_db/re_coco_gt /img_db/re_coco_gt /txt_db/refcoco_train.db Traceback (most...

how to generate image feature from ground true?

1

how to generate image feature from ground true? the code just provide the stript that generates the image from detected bbx instead of ground true.

if you are going to provid the code about extracting feature from a image?

7

Hi, Thank you for your gret job. if you are going to provid the code about extract feature from a image? as current code is no easy to be used...

hi, are you going to release the Web CapFilt dataset?

Hi, thank you for the great job. I just have a question this. Do you plan to release the pretrained model which is just trained in-domain dataset.