ucbrise/piranha

Low accuracy of LeNet

Opened this issue · 4 comments

llCurious commented

Hey. I try to run the experiments for LeNet model. However i noticed that the convergence of LeNet is weird. The test accuracy of LeNet remains low (far from 98%). I only changed the localhost_config.json to run locally with the following configurations:

  1. 3PC computation based on Falcon
  2. network: files/models/lenet.json
  3. batch size: 128
  4. epoch: 5
  5. lr: 2^-4
  6. precision: 16

The output is as follows:
image

llCurious commented

Hey, @jlwatson. Sry to bother you. But do you have any ideas?

jlwatson commented

Hey! I can't immediately run some tests, but as a starting point, could you try running it with models/lenet-norelu.json?

That's the actual LeNet architecture we evaluated with, it just doesn't have the last relu layer, which doesn't interact well with our loss function.

llCurious commented

Thanks to you quick reply!!
I just run the model of lenet-norelu. The accuracy results seems to work fine. BTW, do you mean for other networks like secureml, minionn and so on, I should remove the last relu layer?
image

jlwatson commented