interpreting decode() about darkflow HOT 2 CLOSED

@MarcGroef I am so so so looking forward to your modifications (for better arrangement of code, efficiency, etc). Cheers for taking the time to look at my code.

First, the loss calculation is not only done in decode() - which uses the network output and placeholders' value to calculate the loss, it starts from the moment minibatches of data are yielded by data.py. I added a lot of comments, please refer to the comment in data.py as well as decode() to understand my approach to calculating YOLO's loss.

Again, I expect my solution to your problem you are stucking at is not the best solution, so I hope you can move on to a better one from mine.

from darkflow.

I'll look into it!
Thanks for the response 👍

Cheers,

from darkflow.