Closed zkf331 closed 2 years ago
You configuration seems to be correct. You should be able to achieve 83%~84% easily under this setting. We will release training code after publication.
@zkf331
We have identified your problem. Please use batch size 64 and only single GPU to train this model. When using larger batch size such as 256, the accuracy drops. We doubt this is related to some local minima issue when using large batch size.
Train ZenNet-2.0M in CIFAR100
Test model: zennet_cifar100_model_size2M_res32
Data augmentation:
Train optimizer:
Hi, your work is exciting and inspires us a lot. So we try to reproduce,but we train the test model according to the above configuration, and the training top-1 accuracy is only 80% in cifar100. Did we make a mistake or miss something?