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
I have a question concerning training from scratch. I checked the source code, and it seems that there is no implementation of position embedding. One can only load position embedding from the pretrained models. If I want to train from scratch, should I implement position embedding by myself, or is there something I overlooked? Any other things I should be careful with if training from scratch?
The text was updated successfully, but these errors were encountered:
Training from scratch is the same as position embedding in the source code, the difference is that it doesn't initialize with pre-train weights.
Referring to the author's code, the author initializes the weights with the normal distribution (std=0.02).
Thanks for your work.
I have a question concerning training from scratch. I checked the source code, and it seems that there is no implementation of position embedding. One can only load position embedding from the pretrained models. If I want to train from scratch, should I implement position embedding by myself, or is there something I overlooked? Any other things I should be careful with if training from scratch?
The text was updated successfully, but these errors were encountered: