Skip to content

Latest commit

 

History

History
33 lines (20 loc) · 874 Bytes

README.md

File metadata and controls

33 lines (20 loc) · 874 Bytes

Image Captioning

Implementation of different transfer learning techniques to generate captions for the given image.

Requirements

Install required fundamental packages:

pip3 install torchvision
pip3 install tqdm

The program works well with python version >=3.8.0. Make sure the requirements mentioned here are satisfied, or the result may not be as expected.

Dataset

Get your copy of dataset from here.

Configuration

You can always step ahead and customize the project as you intend to. You need not struggle with the entire program to manage and modify it to your will. It can be done easily by looking into config.py file alone.

Note: In some cases there are limited options available to choose from.

Procedure

Following command trains your model at once:

python3 main.py