Data Science Stack Exchange is a question and answer site for Data science professionals, Machine Learning specialists, and those interested in learning more about the field. It only takes a minute to sign up.
Sign up to join this community
I use Mask RCNN for object detection and instance segmentation. I am new to neural networks, this is my first project.
I use jupyter notebook. Can I continue learning after shutdown?
I would like start learning from 6 epoch. How can I do it? One epoch ~ 1h. I don't want to waste time, and continue this process. Is it possible?
In order to continue the learning process, you will need to use checkpoints.
# source: https://stackoverflow.com/questions/36356004/continue-training-from-a-specific-epoch
weight_save_callback = ModelCheckpoint('/path/to/weights.{epoch:02d}-{val_loss:.2f}.hdf5', monitor='val_loss', verbose=0, save_best_only=False, mode='auto')
model.fit(X_train,y_train,batch_size=batch_size,nb_epoch=nb_epoch,callbacks=[weight_save_callback])
# load model
model = Sequential()
model.add(...)
model.load('path/to/weights.hf5')
# use model.fit to continue training.
