Closed HazSyl1 closed 1 month ago
LGTM but can you remove the empty "Image Captioning/Model Files/Readme.md.bak" file if it has no use?
I've removed "Image Captioning/Model Files/Readme.md.bak".
Hi @HazSyl1 , good work , but please add images of of your results and accuracy with different pretrained model or CNN, And i found your code is not much readable , No Image preprocessing (visualize) , try to add accuracy chart as well
@HazSyl1 any update ,otherwise will close the PR.
Yes the task is almost done . I'll be pushing the complete repo in a while.
Hi, in the latest commit. I've elaborated the code clearly and concisely. And I've performed model testing and evaluation mentioning the scores as well. Apart from this, I've added visualization of the architecture used and how its filters affect the image to get a feature map.
Added notebooks, data, and relevant information on image captioning using deep learning. The process is briefly explained in the README file, along with the model diagram. Resolves #658 .