Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
xinyiW915
/
ReLaX-VQA
like
1
Visual Question Answering
5 datasets
deep-learning
vision
VQA
Transformer
CNN
arxiv:
2407.11496
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
ReLaX-VQA
/
src
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
Xinyi Wang
first commit
211b431
5 months ago
data_processing
first commit
5 months ago
extractor
first commit
5 months ago
utils
first commit
5 months ago
demo_test_gpu.py
Safe
13.1 kB
first commit
5 months ago
feature_fragment_layerstack.py
Safe
16 kB
first commit
5 months ago
feature_fragment_pool.py
Safe
16.6 kB
first commit
5 months ago
feature_layerstack.py
Safe
11.6 kB
first commit
5 months ago
feature_pool.py
Safe
12.4 kB
first commit
5 months ago
main_relaxvqa_feats.py
Safe
12.6 kB
first commit
5 months ago
model_finetune.py
Safe
15 kB
first commit
5 months ago
model_regression.py
Safe
34.1 kB
first commit
5 months ago
model_regression_simple.py
Safe
33.4 kB
first commit
5 months ago
relax_vqa.py
Safe
7.58 kB
first commit
5 months ago