BestiVictory/ILGnet

Random output value for same image

brunnoattorre opened this issue · 3 comments

Upon running the test.py on the same image over multiple times, I get random output numbers as results. Variations are quite big ranging from 0.1 to 0.8 and 0.9. I'm using caffe 1.0.0

I experience the same issue, any help is appreciated.

Even I experienced the same issue..but fixed it by setting np.random.seed() and caffe.set_random_seed().
Try setting these values to whatever you want and you will get the same result afterwards. Hope it helps.

Sorry, the deploy.prototxt before is wrong, we have uploaded the correct file, please re-check the result.