2020-09-20 16:20:55 -0600 | received badge | ● Nice Question (source) |
2020-09-16 09:52:00 -0600 | asked a question | Haar cascade detector with non-maxima suppression Haar cascade detector with non-maxima suppression Dear all, I know the Haar-cascade detectors are kind of old-fashioned |
2020-07-27 07:48:16 -0600 | commented answer | NMSBoxes output with top_k parameter Alright ! Thanks for spotting it !! I though it was ordered as 1, 3, 2 (loop to compute pairwise overlap, until top_k |
2020-07-27 07:36:58 -0600 | marked best answer | NMSBoxes output with top_k parameter Hi all,
the If that's the case, I have an unexpected output when setting top_k to a value >0. The bounding boxes with index 4, 100, 72 and 17 are indeed the one I want, so I can use top_k<0 and select the top_4 afterwards but I though setting top_K in the NMS could stop the NMS earlier and thus save time. I am using Thanks ! EDIT: Test code |
2020-07-27 07:36:58 -0600 | received badge | ● Scholar (source) |
2020-07-27 04:21:40 -0600 | received badge | ● Student (source) |
2020-07-27 04:20:16 -0600 | commented question | NMSBoxes output with top_k parameter I added a test code, with 2 calls to NMSBoxes: with and without the top_k parameters. With top_k=5, it returns only 3 d |
2020-07-27 04:16:03 -0600 | commented question | NMSBoxes output with top_k parameter I added a test code, with 2 calls to NMSBoxes: with and without the top_k parameters. With top_k=5, it returns only 3 d |
2020-07-27 04:11:27 -0600 | received badge | ● Editor (source) |
2020-07-27 04:11:27 -0600 | edited question | NMSBoxes output with top_k parameter NMSBoxes output with top_k parameter Hi all, the top_K parameter in the cv2.dnn.NMSBoxes correspond to the maximum numbe |
2020-07-23 08:49:37 -0600 | asked a question | NMSBoxes output with top_k parameter NMSBoxes output with top_k parameter Hi all, the top_K parameter in the cv2.dnn.NMSBoxes correspond to the maximum numbe |
2020-07-23 07:59:51 -0600 | answered a question | accelerate OpenCV functions on gpu through CUDA Hello, As far as I know you would need to compile the opencv python bindings from source to activate the CUDA support. |