问题
I'm looking to train my own object detector using YOLO 3 for a single class. Basically, it needs to detect whether the test images have the object or not. I face an error where the training doesn't begin and exits with an assertion '0' failed. I checked other answers which say that the CRLF must be encoded as LF for it to work on linux. But that solution doesn't work either. I'm following all the steps outlined in pjreddie's website!
回答1:
The error happens due to image size or with batch size (also sometimes with sub-division also).
You can try to tune the parameters to lower values.
回答2:
Okay, so what helped was re-starting the server and re-doing everything from the beginning. It hasn't happened again, so I think it was just a random error? I'm not sure though. I will try to look into it further.
来源：https://stackoverflow.com/questions/54857673/yolo-3-assertion-0-failed-error-not-crlf-error