RetinaNet_Tensorflow_Rotation
RetinaNet_Tensorflow_Rotation copied to clipboard
Rotation is not accurate as R2CNN
I have trained a model but why is the output more than often making a plus sign. So the horizontal detection is coming along with another detection vertically making a plus sign. I don't know why is it happening ?
can you give me a example result and which cfgs file do you use?
The 180-degree range may have a plus sign. I'm not sure if it is a visualization problem, but I didn't check it out. This situation is reduced when using large models, and I suspect it is caused by angular periodicity. @dexception
Is it like the first line, the other box is suppressed by nms with low NMS_IOU_THRESHOLD = 0.1.
Like the first picture but 2 detections for each object. One horizontal and one vertical thus making a plus sign. Out of 20 objects 12 are having this plus sign.