This project helps captioning images using various concepts like MLP, CNN, RNN, Language models, Word embeddings and Transfer Learning (with RESNET)
Dataset Link: https://www.kaggle.com/datasets/shadabhussain/flickr8k
total images = 8000 1 image has 5 captions total captions = 40,000
Glove 6B50D: https://www.kaggle.com/datasets/watts2/glove6b50dtxt
Below captions are generated by this model.
