ready to get started?
Receive news, announcement and reports
In this project, we created an AI model which can generate text or caption the given image. For this project, we have used an encoder-decoder transformer, so the encoder is a Convolution Neural Network that will process the input image and create a middle output which will be passed to the decoder with a Recurrent Neural Network for generating the text from the middle output of the encoder.
Technologies used
We have used Python, PyTorch, and OpenCV to create this project. We have built the encoder-decoder transformer model.
Difficulties we faced
No major difficulties were faced during this project.
Solutions
No major difficulties were faced during this project.
Receive news, announcement and reports
A-1205, PNTC, Times Of India Press Rd, Vejalpur, Ahmedabad, Gujarat 380015
IN: +91 9157652641 info@tesseracttechnolabs.com
© 2022 All Rights Reserved | Tesseract Technolabs | Privacy Policy | Terms & Conditions