clip-vil/CLIP-ViL

Issues

• How to infer captions on my own images

  #31 opened a year ago by victorup
  1

• How to reproduce the results of experiments that are shown in Table 7

  #33 opened a year ago by raven38
  1

• Where can I found annotations for SNLI-VE?

  #32 opened a year ago by 1219521375
  1

• Wrong visualization results of ViT-B/16 in gradcam_clip.ipynb

  #35 opened a year ago by wangq95
  0

• No 'tfm_gen' when trying to run feature extraction for vqa mcan

  #29 opened 2 years ago by fallcat
  1

• Checkpoint for GQA model

  #12 opened 3 years ago by aurooj
  1

• pretrained weigths for VQA

  #34 opened 2 years ago by guanhdrmq
  0

• Checkpoint for SNLI-VE

  #26 opened 2 years ago by sramshetty
  2

• Pythia Feature Extraction

  #28 opened 2 years ago by shamanthak-hegde
  1

• Data dir for mcan_clip_grid_feature.py

  #24 opened 3 years ago by Fly2flies
  1

• Extracting image features using RN50 for Pythia

  #27 opened 3 years ago by shamanthak-hegde
  0

• About precompute

  #25 opened 3 years ago by StylesZhang
  2

• error in clip extraction code: precomute_imagenet_views.py

  #23 opened 3 years ago by wangqian621
  3

• Errors occurred when extracting clip features using Resnet

  #22 opened 3 years ago by tianjunyu0871
  1

• Errors occurred when extracting clip features using ViT-B/32

  #21 opened 3 years ago by tianjunyu0871
  1

• Captioning model training script fails

  #2 opened 4 years ago by j-min
  11

• The extracted feature of the COCO dataset for caption

  #18 opened 3 years ago by liujiaheng
  4

• The clip_feature

  #19 opened 3 years ago by Timon0327
  1

• CLIP-VIT-B-Transformer captioning results

  #20 opened 3 years ago by YuanEZhou
  1

• About the training time of Pythia

  #15 opened 3 years ago by tingxueronghua
  2

• Train with a single GPU

  #16 opened 3 years ago by ruinianxu
  1

• The links to download CLIP features on the R2R/RxR environment are invalid.

  #17 opened 3 years ago by chenguanqi
  2

• bug in positional_embedding's weights when resizing.

  #13 opened 3 years ago by jianjieluo
  2

• Missed Link

  #11 opened 3 years ago by jdiazram
  1

• configuration file for CLIP-Res50x4

  #10 opened 4 years ago by itsyoavshalev
  1

• evaluating vqa using pythia

  #9 opened 4 years ago by itsyoavshalev
  1

• Grad-CAM visualization code

  #7 opened 4 years ago by yangbang18
  1

• Grad-CAM visualization code

  #8 opened 4 years ago by yangbang18
  0

• Pretrained weights for image captioning

  #6 opened 4 years ago by zhuang93
  1

• How to combine CLIP with Oscacr(or VinVL)?

  #4 opened 4 years ago by 594422814
  1

• About clip feature extraction

  #5 opened 4 years ago by LittleDonkey1203
  1

• Why weights of R-50-grid.yaml is commented out?

  #3 opened 4 years ago by tshu-w
  0

• MS COCO Caption scores with MLE objective

  #1 opened 4 years ago by j-min
  1