|The experiment must have run at least one epoch.|
Select the blocks you want to copy.
Click Copy blocks with weights icon in the upper left corner of the Modeling canvas.
Select from which epoch you want to copy the weights.
Select if you want to set the copied blocks as non-trainable.
Non-trainable means that the block’s weights will not be updated during training of the new experiment. This is a good choice the first time you copy blocks.
Trainable means that the blocks can be trainable with for example new data, that is, the weights associated with the blocks will be updated during training of the new experiment.
Open a new experiment and paste the copied blocks.
For more information, see Copy blocks with weights from another model.
Stay in the know by signing up for occasional emails with tips, tricks, deep learning insights, product updates, event news and webinar invitations.
We promise not to spam you or share your email with any third party. You can change your preferences at any time. See our privacy policies.
Please check your email inbox account to confirm, set, or update your communication preferences.