Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
<u><b>We are creating a spatial aware vision-language(VL) model.</b></u>
|
| 2 |
|
| 3 |
This is a trained model on COCO dataset images including extra information regarding the spatial relationship between the entities of the image.
|
|
@@ -6,7 +19,8 @@ This is a sequence to sequence model for image-captioning. The architecture is <
|
|
| 6 |
|
| 7 |
<details>
|
| 8 |
<summary>Requirements!</summary>
|
| 9 |
-
- 4GB RAM.
|
|
|
|
| 10 |
</details>
|
| 11 |
|
| 12 |
The way to download and run this:
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- ydshieh/coco_dataset_script
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- code_eval
|
| 9 |
+
library_name: transformers
|
| 10 |
+
pipeline_tag: image-to-text
|
| 11 |
+
tags:
|
| 12 |
+
- text-generation-inference
|
| 13 |
+
---
|
| 14 |
<u><b>We are creating a spatial aware vision-language(VL) model.</b></u>
|
| 15 |
|
| 16 |
This is a trained model on COCO dataset images including extra information regarding the spatial relationship between the entities of the image.
|
|
|
|
| 19 |
|
| 20 |
<details>
|
| 21 |
<summary>Requirements!</summary>
|
| 22 |
+
- 4GB GPU RAM.
|
| 23 |
+
- CUDA enabled docker
|
| 24 |
</details>
|
| 25 |
|
| 26 |
The way to download and run this:
|