CPG

CPG copied to clipboard

Why training speed slows down after 314 batch size and accuracy=nan in Step 3 of Experiment3 ?

1

Skipped 6000 image pairs 2022-01-08 18:00:28,652 - root - INFO - 2022-01-08 18:00:28,652 - root - INFO - Before pruning: 2022-01-08 18:00:28,652 - root - INFO - Sparsity range: 0.0...

yanglinxiabuaaa

Hi! Is it possible to use model trained on 4 facial-informatic tasks in a way that it can produce predictions for all tasks in single forward pass? Something like in...

yurakuratov

About number of parameters

1

Thanks for your work and code. I‘m a bit confusing after reading the code. I'd like to know whether the mask and piggymask are different thing, the former works for...

gaogg

Some question about CPG_cifar100_scratch_mul_1.5.sh

2

Thanks for this great work I have two questions about CPG_cifar100_scratch_mul_1.5.sh I run this .sh to complete experiment1 step3 to achieve my adversarial training project. When I run the first...

rmp918

Hi, Thanks for the great work. I have a question with regard to your gradual prune implementation. I notice that in your implementation, you commented out the code for masking...

thomascong121

How do you get the same performance for a previous task?

1

Hi, thanks for the great work. I try to use your code for my own project, however, I find it is hard to obtain the same accuracy on the previously...

thomascong121