retinanet.pytorch

retinanet.pytorch copied to clipboard

@andreaazzini HI For focal loss. The **classification branch** uses the **sigmoid function**. Why **background class** is considered in the classification branch??such as **coco**, num_classes=80 instead of 81.

foralliance

maximum recursion depth exceeded

1

hi, while running the train.py I got this error "maximum recursion depth exceeded " . Can you advice?

Dev2022

Do you have object detection bounding box visualization results?

8

Trying to debug my implementation's training on COCO, would love to see if you got this repo working on VOC.

c0nn3r