from the middle

[ghost]

Hi,

I trained my model by 50,000 iter.
What should I do in order to begin to also learn from the middle?

[last-one]

Sorry, I don't know. This is about PyTorch, and I don't know how to save the middle parameters with PyTorch, like caffe's solverstate or tf's checkpoint. So I don't know how to restore from the middle.

[last-one]

If you just want to use the middle model without middle state information, you can load the middle model directly to initialize the model.

[ghost]

Thank you for your replying.