Test accuracy stays the same about pytorch-nin-cifar10 HOT 7 CLOSED

To follow up with this, I ran it exactly the same way once again just to give another shot. Then it started working. Have you ever experienced such situation / know why this happens?

from pytorch-nin-cifar10.

@hyojinie Hi, can you try using a lower learning rate like 0.01? 0.1 sometimes works but sometimes not. It is related to the initialization.

You can easily change the learning rate by changing the line here.

from pytorch-nin-cifar10.

0.03 might be better if the training coverages successfully.

from pytorch-nin-cifar10.

Thanks a lot for your response. I recognize it is due to initialization as well. Would lowering learning rate still help when initialization is not favorable? My friends suggest using batch normalization to be less sensitive to the initialization. I might try that. Thanks a lot for the help.

from pytorch-nin-cifar10.

@hyojinie Yes, batch normalization should help a lot and the accuracy can be increased to around 91% (I cannot remember clearly but it should be around 91.3% something). For initialization which is not favorable, without batch normalization, a typical strategy is to use lower learning rate to "warm up" the training and then switch to a higher learning rate.

from pytorch-nin-cifar10.

Cool. Thanks a lot for the helpful insights.

from pytorch-nin-cifar10.

I wonder if 89.64% was achieved with learning rate 0.03? I tried it twice, but the accuracy was around 88% and 88.90% with batch normalization.

from pytorch-nin-cifar10.