Focal_loss_for_object_detection
Focal_loss_for_object_detection copied to clipboard
Retinanet impelemented by Pytorch : 69.0 mAP on VOC2007 test.
Hi, For input size 384*384, which places of code do I have to modify? Thanks
I use the function decode in the encoder.py, always have the fellowing question. Traceback (most recent call last): File "eval.py", line 281, in test() File "eval.py", line 238, in test...
Thinks for sharing. But when I run eval.py it appear that error. File "/home/zt/pytorch/Focal_loss_for_object_detection-master/encoder.py", line 129, in decode keep = box_nms(boxes[ids], score[ids], threshold=NMS_THRESH) RuntimeError: invalid argument 2: sizes do not...