Update README.md
Browse files
README.md
CHANGED
|
@@ -65,15 +65,14 @@ Starting with `transformers` version >= 4.45.0, you can run **conversational inf
|
|
| 65 |
|
| 66 |
To use LISAT-7B with transformers, make sure to update your transformers installation to the latest version using:
|
| 67 |
|
| 68 |
-
|
| 69 |
-
pip install --upgrade transformers
|
| 70 |
|
| 71 |
Once your installation is updated, you can use LISAT-7B for inference as follows:
|
| 72 |
|
| 73 |
|
| 74 |
This will render as a properly formatted Python code snippet in Markdown. When you view it in a Markdown-rendering environment, it will look like this:
|
| 75 |
|
| 76 |
-
|
| 77 |
from transformers import AutoModelForImageSegmentation, AutoTokenizer
|
| 78 |
|
| 79 |
# Load model and tokenizer
|
|
@@ -85,7 +84,7 @@ input_image = "path/to/your/image.png" # Replace with your input image
|
|
| 85 |
inputs = tokenizer(input_image, return_tensors="pt")
|
| 86 |
|
| 87 |
# Generate segmentation or other tasks
|
| 88 |
-
outputs = model.generate(**inputs)
|
| 89 |
|
| 90 |
|
| 91 |
## Intended Use
|
|
@@ -150,14 +149,14 @@ If you use LISAt in your research or applications, please cite our paper:
|
|
| 150 |
|
| 151 |
If you use LISAt in your research or applications, please cite our paper:
|
| 152 |
|
| 153 |
-
|
| 154 |
@article{TBD,
|
| 155 |
title={LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery},
|
| 156 |
author={Quenum, Jerome and Hsieh, Wen-Han and Wu, Tsung-Han and Gupta, Ritwik and Darrell, Trevor and Chan, David M},
|
| 157 |
journal={TBD},
|
| 158 |
year={2025},
|
| 159 |
url={TBD}
|
| 160 |
-
}
|
| 161 |
|
| 162 |
|
| 163 |
|
|
|
|
| 65 |
|
| 66 |
To use LISAT-7B with transformers, make sure to update your transformers installation to the latest version using:
|
| 67 |
|
| 68 |
+
`pip install --upgrade transformers`
|
|
|
|
| 69 |
|
| 70 |
Once your installation is updated, you can use LISAT-7B for inference as follows:
|
| 71 |
|
| 72 |
|
| 73 |
This will render as a properly formatted Python code snippet in Markdown. When you view it in a Markdown-rendering environment, it will look like this:
|
| 74 |
|
| 75 |
+
`
|
| 76 |
from transformers import AutoModelForImageSegmentation, AutoTokenizer
|
| 77 |
|
| 78 |
# Load model and tokenizer
|
|
|
|
| 84 |
inputs = tokenizer(input_image, return_tensors="pt")
|
| 85 |
|
| 86 |
# Generate segmentation or other tasks
|
| 87 |
+
outputs = model.generate(**inputs)`
|
| 88 |
|
| 89 |
|
| 90 |
## Intended Use
|
|
|
|
| 149 |
|
| 150 |
If you use LISAt in your research or applications, please cite our paper:
|
| 151 |
|
| 152 |
+
`bibtex
|
| 153 |
@article{TBD,
|
| 154 |
title={LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery},
|
| 155 |
author={Quenum, Jerome and Hsieh, Wen-Han and Wu, Tsung-Han and Gupta, Ritwik and Darrell, Trevor and Chan, David M},
|
| 156 |
journal={TBD},
|
| 157 |
year={2025},
|
| 158 |
url={TBD}
|
| 159 |
+
}`
|
| 160 |
|
| 161 |
|
| 162 |
|