Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,12 @@ Each model integrates a robust visual encoder and a natural language processing
|
|
| 9 |
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## **Hyperparameters**
|
| 13 |
|
| 14 |
The following table summarizes the key training configurations used for each model:
|
|
|
|
| 9 |
|
| 10 |
---
|
| 11 |
|
| 12 |
+
## **Data**
|
| 13 |
+
|
| 14 |
+
This project uses the [COCO dataset](https://cocodataset.org/) for training and evaluation, which consists of images with multiple human-annotated captions.
|
| 15 |
+
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
## **Hyperparameters**
|
| 19 |
|
| 20 |
The following table summarizes the key training configurations used for each model:
|