How do i resume my training on colab?

[kartikJ-9]

Decent results require 3k-5k frames. My GPU session on colab gets disconnected due to usage while training. I am saving the checkpoints in the drive. Is there any way I can resume the training from a particular epoch? I have a sequence of images obtained from a video.

[junyanz]

I assume that you are using the Pytorch version with colab. For Lua, you can use continue_train flag. For PyTorch, please see this Q & A.