In this project, I have created a neural network architecture to automatically generate captions from images. After using the Microsoft Common Objects in COntext (MS COCO) dataset to train my network, I have tested my network on novel images!
How to run:
- Run 0_Dataset file
- Then 1,2,3 files
- model.py contains the architecture CNN-RNN model which you can modify if you want to experiment.
- Dataloader loads the data.
Please refer to my blog to know more: https://blog.goodaudience.com/automatic-image-captioning-building-an-image-caption-generator-from-scratch-4bdd8744bc38?sk=0cd300a528a02be0596f3e042a82f7a4
LinkedIn: https://www.linkedin.com/in/garima-nishad-9b8385134/
Follow me on Twitter: https://twitter.com/garima__nishad