Different Results on GPU vs CPU

[VisionEp1]

see last comment- better problem description

[VisionEp1]

update it happens also with the normal pre trained yolov4 file
yolov4.cfg.txt

i used the most recent opencv version + the most recent darknet.

windows with cmake (one time i disabled cuda+cudnn via cmake the other time i didnt)

4-5% confidence difference seems huge to me

[VisionEp1]

or with lower confidence. even more different

[VisionEp1]

after days of testing.

avx is the issue after forcing is_avx to -1 everything works perfect.
might be linked with
see issue: #5793

[truongbv1]

Hi, @AlexeyAB
I see another bug that causes different results on GPU and CPU
GPU=1 - working properly
GPU=0 - not working properly
with GPU=0, you missed the case of RELU6 in float activate(float x, ACTIVATION a), if use RELU6 activation func then all return 0