Image Captioning Using GPT-2 and CLIP

In the last few years, the problem of generating descriptive sentences automatically for images have gained arising interest.Image captioning is a task where each image must be understood properly and are able generate suitable caption with proper grammatical structure. Automatically creating the description or caption of an image using any natural language sentences is a very challenging task. It requires both methods from computer vision to understand the content of the image and a language model from the field of natural language processing  to turn the understanding of the image into words in the right order.Our project aims to implement an Image caption generator that responds to the user to get the captions for a provided image. The ultimate purpose of Image caption generator is to make users experience better by generating automated captions. The combination of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) such as long short-term memory (LSTM) has been shown to be effective in addressing this challenge. In this study, we introduce an image caption generator that utilizes both CNN and LSTM architectures. The CNN extracts visual features from the input images, which are then fed to the LSTM for generating descriptive sentences