This is an image to caption generator deep learning model.

Uses both NLP + Computer Vision.

Model used: DenseNet201(Pretrained CNN model for image processing) + LSTM(For captions).

How to run it:

1. Clone this repository.

2. Install the requirements.

pip install -r requirements.txt

3. Run the streamlit app.

streamlit run main.py

Note: Use python version<=3.11 (For tensorflow compatibility).