Does the code have Settings for model saving about pycil HOT 3 CLOSED

Can you rephrase your problem more clearly? (Questions written in Chinese are also acceptable)

from pycil.

Do you mean how to save models trained after each incremental session?

Please add self.save_checkpoint(filename) in the function after_task of the method you choose to run.

from pycil.

Do you mean how to save models trained after each incremental session?

Please add self.save_checkpoint(filename) in the function after_task of the method you choose to run.

不好意思，我使用der的方法 在after_task后保存了权重，我发现这个方法模型的结构会动态的变化，全连接层也会改变，我根据变化的网络分别加载保存出来的权重 ，发现跟工具箱中的准确率都很大的区别，工具箱在初始训练7，增量1的条件下，基本能保持百分之90多，但是我自己单独拿出来测的话 在cifar10上测试，acc准确率很低。请问能帮我解决一下么

from pycil.