Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

reg_best does not converge #16

Open
snutesh opened this issue Feb 17, 2023 · 1 comment
Open

reg_best does not converge #16

snutesh opened this issue Feb 17, 2023 · 1 comment

Comments

@snutesh
Copy link

snutesh commented Feb 17, 2023

I tried to use pretrained backdoor model on CIFAR10 dataset. But during visualization none of values among cost, attack, loss, ce, reg, reg_best gets updated.
Here is the snapshot:

loading dataset
X_test shape (50, 32, 32, 3)
Y_test shape (50, 10)
loading model
processing label 7
resetting state
('mask_tanh', -3.672258450327029, 3.5073656483843307)
('pattern_tanh', -3.9436355297972994, 4.010161127999756)
step: 0, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 528.047913, reg_best: inf
step: 1, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 547.919495, reg_best: inf
step: 2, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 3, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 4, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
down cost from 0.00E+00 to 0.00E+00
step: 5, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 6, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 7, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 8, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
step: 9, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf
down cost from 0.00E+00 to 0.00E+00
step: 10, cost: 0.00E+00, attack: 0.000, loss: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf

@wxx336
Copy link

wxx336 commented Feb 24, 2025

我尝试在 CIFAR10 数据集上使用预训练的后门模型。但在可视化期间,cost、attack、loss、ce、reg reg_best 之间的值都不会更新。这是快照:

加载数据集 X_test 形状 (50, 32, 32, 3) Y_test 形状 (50, 10) 加载模型处理标签 7 重置状态 ('mask_tanh', -3.672258450327029, 3.5073656483843307) ('pattern_tanh', -3.9436355297972994, 4.010161127999756) 步长: 0, 成本: 0.00E+00, 攻击: 0.000, 损失: 16.118097, CE: 16.118097, 注册: 528.047913, reg_best: inf步骤:1,成本:0.00E+00,攻击:0.000,损失:16.118097,ce:16.118097,注册:547.919495,reg_best:inf 步骤:2,成本:0.00E+00,攻击:0.000,损失:16.118097,ce:16.118097,注册:548.243958,reg_best:inf 步骤:3,成本:0.00E+00,攻击:0.000,损失:16.118097,ce:16.118097,注册:548.243958,reg_best:inf 步骤:4,成本:0.00E+00,攻击:0.000,损失: 16.118097,ce:16.118097,reg:548.243958,reg_best:inf 降低成本从 0.00E+00 到 0.00E+00 步骤:5,成本:0.00E+00,攻击:0.000,损失:16.118097,ce:16.118097,reg:548.243958,reg_best:inf 步骤:6,成本:0.00E+00,攻击:0.000,损失:16.118097,ce:16.118097,reg:548.243958,reg_best:inf 步骤:7,成本:0.00E+00,攻击:0.000,损失: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf 步骤: 8, 成本: 0.00E+00, 攻击: 0.000, 损失: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf 步骤: 9, 成本: 0.00E+00, 攻击: 0.000, 损失: 16.118097, ce: 16.118097, reg: 548.243958, reg_best: inf 降低成本从 0.00E+00 到 0.00E+00 步骤: 10, 成本: 0.00E+00, 攻击: 0.000, 损失: 16.118097,CE:16.118097,注册:548.243958,reg_best:inf

请问你是如何做的实验,使将自己的数据集和模型整理为源代码需要的.h5格式,还是用自己的数据集.h5格式重新训练感染模型的,我这里弄不清楚,已经做了很久了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants