Christopher Lennan

Hi, yes, I guess you could train a model on text readability in images. You would need a labeled dataset with many examples of varying degrees of readability and their...

Hi, have you followed the steps in our documentation on how to create a dataset and train a model?

Hi, thanks a lot for the PR! It's a great idea to add a Flask server to the repo - there are a few things that need to be addressed...

Yes, highest score is 10, lowest is 1

Sorry, difficult to debug Windows errors as I am using a Unix system. Are you using Docker for whatever you are trying to do?

Hi, we inferred the distribution from mean scores in a crude way, such that each distribution is monotonically increasing or decreasing. There are definitely more sophisticated ways to do that,...

Hi, what we did for TID2013 is to infer a probability distribution from the reported mean score. Then we passed the inferred distribution as labels throughout training with an EMD...

Good point. Will add it to next release