README.md

metadata

title: Image Captioning Demo
emoji: 📷
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false

Image Captioning Demo

This Space demonstrates an Image Captioning model trained on a custom dataset with 6000 training images. Upload an image to generate a caption.

Model Details

• Image Encoder: ResNet50
• Text Decoder: LSTM with fine-tuned GloVe embeddings
• Vocabulary Size: 3478
• Max Caption Length: 20
• Sampling: Top-k (k=5)

Example

• Input: Image of a dog
• Output: "A dog is running in the park"

Usage

1. Upload an image in PNG or JPEG format.
2. Click "Submit" to generate a caption.

License

MIT