issues
search
TheoCoombes
/
ClipCap
Using pretrained encoder and language models to generate captions from multimedia inputs.
94
stars
15
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Evaluation using pre-trained model
#8
uu95
opened
1 year ago
1
train and release models
#7
rom1504
opened
2 years ago
0
minimal usage instruction
#6
rom1504
opened
2 years ago
2
Create python-publish.yml for automated release
#5
rom1504
closed
2 years ago
2
Release a pretrained model and add inference example
#4
rom1504
opened
2 years ago
0
inference
#3
tkone2018
opened
2 years ago
2
Experimental: Optionally use all ViT features of CLIP
#2
andreaskoepf
closed
2 years ago
1
Inference metrics: Bleu, METEOR, ROUGE_L, CIDEr, SPICE
#1
igor0
closed
2 years ago
0