Spaces:
Sleeping
Sleeping
Delete README.md
Browse files
README.md
DELETED
@@ -1,63 +0,0 @@
|
|
1 |
-
# Multi-Modal AI Demo
|
2 |
-
|
3 |
-
This project demonstrates the use of multi-modal AI capabilities using Hugging Face pretrained models. The application provides the following features:
|
4 |
-
|
5 |
-
1. **Image Captioning**: Generate descriptive captions for images
|
6 |
-
2. **Visual Question Answering**: Answer questions about the content of images
|
7 |
-
3. **Sentiment Analysis**: Analyze the sentiment of text inputs
|
8 |
-
|
9 |
-
## Requirements
|
10 |
-
|
11 |
-
- Python 3.8+
|
12 |
-
- Dependencies listed in `requirements.txt`
|
13 |
-
|
14 |
-
## Installation
|
15 |
-
|
16 |
-
1. Clone this repository
|
17 |
-
2. Install dependencies and setup the application:
|
18 |
-
```
|
19 |
-
python run.py
|
20 |
-
```
|
21 |
-
Then select option 5 to perform full setup (install requirements, fix dependencies, and download sample images)
|
22 |
-
|
23 |
-
## Known Issues and Solutions
|
24 |
-
|
25 |
-
If you encounter errors related to package compatibility (Pydantic, FastAPI, or Gradio errors), use:
|
26 |
-
```
|
27 |
-
python fix_dependencies.py
|
28 |
-
```
|
29 |
-
This will install compatible versions of all dependencies to ensure the application runs correctly.
|
30 |
-
|
31 |
-
## Usage
|
32 |
-
|
33 |
-
Run the web interface:
|
34 |
-
```
|
35 |
-
python app.py
|
36 |
-
```
|
37 |
-
|
38 |
-
Then open your browser and navigate to the URL shown in the terminal (typically http://127.0.0.1:7860).
|
39 |
-
|
40 |
-
## Deploying to Hugging Face Spaces
|
41 |
-
|
42 |
-
To deploy this project to Hugging Face Spaces:
|
43 |
-
|
44 |
-
1. Create a new Space on [Hugging Face Spaces](https://huggingface.co/spaces)
|
45 |
-
2. Choose the "Gradio" SDK
|
46 |
-
3. Set up GitHub repository with these files:
|
47 |
-
- `app.py`
|
48 |
-
- `model_utils.py`
|
49 |
-
- `requirements.txt`
|
50 |
-
- `README.md`
|
51 |
-
4. Push to the repository connected to your Space
|
52 |
-
5. Hugging Face will automatically deploy your application
|
53 |
-
|
54 |
-
## Models Used
|
55 |
-
|
56 |
-
This demo uses the following pretrained models from Hugging Face:
|
57 |
-
- Image Captioning: `nlpconnect/vit-gpt2-image-captioning`
|
58 |
-
- Visual Question Answering: `nlpconnect/vit-gpt2-image-captioning` (simplified)
|
59 |
-
- Sentiment Analysis: `distilbert-base-uncased-finetuned-sst-2-english`
|
60 |
-
|
61 |
-
## License
|
62 |
-
|
63 |
-
MIT
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|