Update README.md
Browse files
README.md
CHANGED
|
@@ -89,7 +89,7 @@ The BridgeTower model was pretrained on four public image-caption datasets:
|
|
| 89 |
- [MSCOCO Captions](https://arxiv.org/pdf/1504.00325.pdf)
|
| 90 |
- [Visual Genome](https://visualgenome.org/)
|
| 91 |
|
| 92 |
-
The total number of unique images in the combined data is around
|
| 93 |
|
| 94 |
## Training procedure
|
| 95 |
|
|
|
|
| 89 |
- [MSCOCO Captions](https://arxiv.org/pdf/1504.00325.pdf)
|
| 90 |
- [Visual Genome](https://visualgenome.org/)
|
| 91 |
|
| 92 |
+
The total number of unique images in the combined data is around 14M.
|
| 93 |
|
| 94 |
## Training procedure
|
| 95 |
|