jessemelpolio / Faster_RCNN_for_DOTA

Code used for training Faster R-CNN on DOTA
https://arxiv.org/abs/1711.10398
Apache License 2.0
336 stars 102 forks source link

how to use the nms method #7

Open auroua opened 6 years ago

auroua commented 6 years ago
from nms2.nms import py_nms_wrapper, cpu_nms_wrapper, gpu_nms_wrapper

boxes2 = np.array([
            [0, 100, 0, 0, 100, 0, 100, 100, 0.99],
            [10, 110, 10, 10, 130, 10, 150, 110, 0.88],#keep 0.68
            [150, 250, 150, 150, 250, 150, 250, 250, 0.77],  # keep 0.0
            [20, 50, 50, 20, 120, 50, 50, 120, 0.66],#discard 0.70
         ], dtype=np.float32)
nms = gpu_nms_wrapper(0.6, 0)
keep = nms(boxes2)
print(keep)

This is a simple test code about the gpunms. The output of this code is [2, 1, 3, 0]. Does this result correct?