Join GitHub today
validation accuracy at 50% instead of 60%? #50
I get 50% accuracy on the ILSVRC2012 validation set without training, which falls short of the 60% boasted in the AlexNet paper (i.e 40.7% top-1 error rate).
Any idea what could be the problem? I'm thinking this could be due to the parameters of the local_response_normalisation layer: yours seem different than the caffe AlexNet here. For instance you have alpha=1e-5 instead of 1e-4. I've been playing with those but have yet to find a configuration that gets me to 60%.
changed the title from
lrn settings inconsistent
validation accuracy at 50% instead of 60%?
May 4, 2018
added a commit
May 7, 2018
thanks for the hint with the normalization factor. I think I remember that I put it for some reason to 1e-5 but it is so long ago and I coudn't find a commit where this was discussed. So I changed it to the publication value again. Regarding the ImageNet validation: I never tried it actually. One thing, while accuracy could probably not match is the difference in image loading ( See this issue). Another reason might be, that you test on single images. In the original AlexNet paper, they worked with 5 random crops from the original 256x256 images and averaged the predictions.