Transfer Learning is the process of training a pre-existing model for new output targets without having to retrain the whole network.
In this project this could look similar to the regular TRAIN subcommand, but where MODEL points to a previously trained .ptl model file.
neuston_net.py TRANSFER <optional_args> SRC MODEL TRAINING_ID
Transfer Learning is the process of training a pre-existing model for new output targets without having to retrain the whole network.
In this project this could look similar to the regular
TRAINsubcommand, but whereMODELpoints to a previously trained .ptl model file.neuston_net.py TRANSFER <optional_args> SRC MODEL TRAINING_ID