Instructions to use noamrot/FuseCap_Image_Captioning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use noamrot/FuseCap_Image_Captioning with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="noamrot/FuseCap_Image_Captioning")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("noamrot/FuseCap_Image_Captioning") model = AutoModelForMultimodalLM.from_pretrained("noamrot/FuseCap_Image_Captioning", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse filesadded links to github
README.md
CHANGED
|
@@ -17,6 +17,10 @@ A framework designed to generate semantically rich image captions.
|
|
| 17 |
|
| 18 |
- ๐ **Demo**: Try out our BLIP-based model [demo](https://huggingface.co/spaces/noamrot/FuseCap) trained using FuseCap, hosted on Huggingface Spaces.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
#### Running the model
|
| 21 |
|
| 22 |
Our BLIP-based model can be run using the following code,
|
|
|
|
| 17 |
|
| 18 |
- ๐ **Demo**: Try out our BLIP-based model [demo](https://huggingface.co/spaces/noamrot/FuseCap) trained using FuseCap, hosted on Huggingface Spaces.
|
| 19 |
|
| 20 |
+
- ๐ **Code Repository**: The code for FuseCap can be found in the [GitHub repository](https://github.com/RotsteinNoam/FuseCap).
|
| 21 |
+
-
|
| 22 |
+
- ๐๏ธ **Datasets**: The datasets used in FuseCap can be accessed from [here](https://github.com/RotsteinNoam/FuseCap#datasets).
|
| 23 |
+
|
| 24 |
#### Running the model
|
| 25 |
|
| 26 |
Our BLIP-based model can be run using the following code,
|