You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Then after 1 epoch (and it's already saved its own checkpoint), I interrupt with Ctrl+C. The day after, I want to continue training with following command:
Work,
some options like epoch/iter count, image size or loss values can be reconfigured, that is why epoch start from 0. It mean "I won't more 100 epoch with lambda_A = 100" for example
And some options like model type or model settings can`t change, if you create pix2pix model, continue to train pix2pix model
I trained
edges2shoes
dataset with following command:Then after 1 epoch (and it's already saved its own checkpoint), I interrupt with
Ctrl+C
. The day after, I want to continue training with following command:You can notice I parse in
--continue_train
option (as I read inoptions/train_options.py
).I notice that generated fake image is kept, but epoch is reset back to 1, loss is also graphed from nothing.
I wonder if this continued training or not? If not, how can I keep training my model after interrupting it.
The text was updated successfully, but these errors were encountered: