jquenum commited on
Commit
f58b842
·
verified ·
1 Parent(s): 0671e58

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -20,7 +20,9 @@ With its advanced reasoning capabilities and superior performance on geospatial
20
 
21
  <!-- ![LISAT Model Architecture](https://huggingface.co/jquenum/LISAt-7b/resolve/main/LISAt.png) -->
22
 
23
- <img src="https://huggingface.co/jquenum/LISAt-7b/resolve/main/LISAt.png" width="600"/>
 
 
24
 
25
  - **Training data**: we introduce the Geospatial Reasoning Segmentation Dataset (GRES), a collection of vision and language data designed around
26
  remote-sensing applications. GRES consists of two core components: PreGRES, a dataset consisting of over 1M remote-sensing specific visual instruction-tuning Q/A pairs for pre-training geospatial models, and GRES, a semi-synthetic dataset specialized for reasoning segmentation of remote-sensing data and consisting of 9,205 images and 27,615 natural language queries/answers within those images. From this LISAt dataset, we generate train, test, and validation splits consisting of 7,205, 1,500, and 500 images respectively.
 
20
 
21
  <!-- ![LISAT Model Architecture](https://huggingface.co/jquenum/LISAt-7b/resolve/main/LISAt.png) -->
22
 
23
+ <p align="center">
24
+ <img src="https://huggingface.co/jquenum/LISAt-7b/resolve/main/LISAt.png" width="300"/>
25
+ </p>
26
 
27
  - **Training data**: we introduce the Geospatial Reasoning Segmentation Dataset (GRES), a collection of vision and language data designed around
28
  remote-sensing applications. GRES consists of two core components: PreGRES, a dataset consisting of over 1M remote-sensing specific visual instruction-tuning Q/A pairs for pre-training geospatial models, and GRES, a semi-synthetic dataset specialized for reasoning segmentation of remote-sensing data and consisting of 9,205 images and 27,615 natural language queries/answers within those images. From this LISAt dataset, we generate train, test, and validation splits consisting of 7,205, 1,500, and 500 images respectively.