Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,3 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# 🇻🇳 Vietnamese Image Captioning Model
|
| 2 |
|
| 3 |
> **EfficientNet-B0 × BARTPho** | *Trained on UIT-ViIC dataset*
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: vi
|
| 3 |
+
license: mit
|
| 4 |
+
tags:
|
| 5 |
+
- image-captioning
|
| 6 |
+
- vision
|
| 7 |
+
- nlp
|
| 8 |
+
- multimodal
|
| 9 |
+
datasets:
|
| 10 |
+
- uit-viic
|
| 11 |
+
metrics:
|
| 12 |
+
- bleu
|
| 13 |
+
- rouge
|
| 14 |
+
- meteor
|
| 15 |
+
- cider
|
| 16 |
+
pipeline_tag: image-to-text
|
| 17 |
+
---
|
| 18 |
# 🇻🇳 Vietnamese Image Captioning Model
|
| 19 |
|
| 20 |
> **EfficientNet-B0 × BARTPho** | *Trained on UIT-ViIC dataset*
|