Downloads · 30 days
6
1% of all-time downloads
VQA-vit5
truong-xuan-linh/VQA-vit5
VQA-vit5 is a machine learning model from truong-xuan-linh. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
Question: - Encoder: ViT5-base - Max length: 32 - Pre-Processing: lower, remove special character
All-time downloads
653
Public
Repo size
77.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin904 MB · 100%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Apr 27, 2024
- Updated
- May 3, 2024
- SHA
- 5c2bd87e
Model card
From the Hugging Face model README
Question:
- Encoder: ViT5-base
- Max length: 32
- Pre-Processing: lower, remove special character
Image:
- Encoder: VIT-base
- Pre-Processing: None
OCR:
-
Text Detection: Paddle OCR
-
Text Recognition: VietOCR
- Threshold: 0.8
-
Max length: 128
-
Post-processing: group layout, divide=4
Answer:
- Max length: 56
Result:
- Dev:
- CIDEr: 3.4616
- BLEU: 0.4689
- Library
- transformers
- Type
- t5
- Created
- Apr 27, 2024
- Updated
- May 3, 2024