Commit
•
e18488b
1
Parent(s):
0273536
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,10 @@
|
|
| 4 |
This model can be used to assign an object-to-caption relatedness score, which is valuable for
|
| 5 |
(1) caption diverse re-ranking, and (2) generate soft labels for caption filtering when scraping image captions from the internet.
|
| 6 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
```
|
| 9 |
conda create -n BERT_visual python=3.6 anaconda
|
|
|
|
| 4 |
This model can be used to assign an object-to-caption relatedness score, which is valuable for
|
| 5 |
(1) caption diverse re-ranking, and (2) generate soft labels for caption filtering when scraping image captions from the internet.
|
| 6 |
|
| 7 |
+
For quick start please have a look this [colab](https://colab.research.google.com/drive/1N0JVa6y8FKGLLSpiG7hd_W75UYhHRe2j?usp=sharing)
|
| 8 |
+
|
| 9 |
+
For the [dataset](https://huggingface.co/datasets/AhmedSSabir/Textual-Image-Caption-Dataset)
|
| 10 |
+
|
| 11 |
|
| 12 |
```
|
| 13 |
conda create -n BERT_visual python=3.6 anaconda
|