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:
- 3PC computation based on Falcon
- network:
files/models/lenet.json
- batch size: 128
- epoch: 5
- lr: 2^-4
- precision: 16
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
jlwatson commented
Hey just to follow up, you should use the versions without the last ReLU
layer -- it plays nicer with our loss function. And LeNet is pretty easy to
train, so I'm not very surprised to see high accuracy after only 5 rounds.
Looks like things are working properly.
…On Fri, Apr 7, 2023 at 2:36 AM llCurious ***@***.***> wrote:
I just check the figures on the paper. The presented figure is only about
97% for training 10 epochs. The above figures that I obtain is for 5
epochs. Is there something wrong with this part?
[image: image]
<https://user-images.githubusercontent.com/21785695/230585340-9c2b1514-730d-4432-a4a6-ca75932d5a23.png>
—
Reply to this email directly, view it on GitHub
<#11 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABMIC4622H26EBOFTXHCA7DW77N3TANCNFSM6AAAAAAWVKBAQY>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>