Skip to content

Latest commit

 

History

History
18 lines (12 loc) · 708 Bytes

README.md

File metadata and controls

18 lines (12 loc) · 708 Bytes

Image Captioning model: Streamlit Demo

Setup

  1. Clone this repository
  2. Install requirements: pip install requirements.txt

Downloading pre-trained model

You can download the pretrained model here and the vocabulary file here.

You should extract pretrained_model.zip and move encoder and decoder .pkl to "models/". Vocab file is already placed in "data/" folder.

Run without UI

run: python inference.py --image="path/to/image"

Using Streamlit UI

  1. run: streamlit ui.py
  2. visit: http://localhost:8501, Upload your image and click on Generate Caption