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
When training rectified_flow_2, the code rectified_flow_2.net = copy.deepcopy(rectified_flow_1) is wrong and useless. In fact, I think you should use rectified_flow_2.model.load_state_dict(rectified_flow_1.model.state_dict()) to load pretrained parameters of rectified_flow_1.
The text was updated successfully, but these errors were encountered:
When training rectified_flow_2, the code
rectified_flow_2.net = copy.deepcopy(rectified_flow_1)
is wrong and useless. In fact, I think you should userectified_flow_2.model.load_state_dict(rectified_flow_1.model.state_dict())
to load pretrained parameters of rectified_flow_1.The text was updated successfully, but these errors were encountered: