Automatic Image Captioning With PyTorch

This is my first open source project . I was selected as a Participant for Open Source Contributions at Student Code-in  . Actually, It was a two months programme where I was selected for contributions to a Computer Vision Project : Image Captioning . In this project,  I design and train a CNN-RNN (Convolutional Neural Network - Recurrent Neural Network) model for automatically generating image captions. I n this case, LSTM (Long Short Term Memory), is used which is a special kind of RNN that includes a memory cell, in order to maintain the information for a longer period of time.   The network is trained on the Microsoft Common Objects in COntext   (MS COCO)  dataset. The image captioning model is displayed below.   Image Source Dataset Used - MS COCO Dataset The COCO dataset is one of the largest, publicly available image datasets and it is meant to represent realistic scenes. What I mean by this is that COCO does not overly pre-process images, instead these images come in a vari