Answer the question
In order to leave comments, you need to log in
What is needed to implement "composing a verbal description of the image"?
I study at the university, I saw the future topics of the WRC, there is a topic "compiling a verbal description of the image." It became curious how to implement this, but I can’t even google something approximate. Can you help, what are you looking for? What to read on this topic and are there any libraries for similar work, for example in python?
Answer the question
In order to leave comments, you need to log in
The task is called image captioning.
Here is a good guide to Pytorch: https://www.analyticsvidhya.com/blog/2018/04/solvi...
Didn't find what you were looking for?
Ask your questionAsk a Question
731 491 924 answers to any question