0

I am training a model which takes a long time to complete an epoch and I would like to be able to record and monitor during training the training and validation loss after each batch rather than epoch.

So currently this is what I get:

enter image description here

My callbacks currently are the following:

##callbacks
cb_checkpoint = ModelCheckpoint("model.h5", monitor='val_loss', save_weights_only=True,save_best_only=True, save_freq=1)
cb_Early_Stop=EarlyStopping( monitor='val_loss',patience=20)
cb_Reduce_LR = ReduceLROnPlateau(monitor='val_loss', factor=0.3, patience=5, verbose=0, mode='auto', min_delta=0.0001, 
                                 cooldown=0, min_lr=0)

callbacks = [cb_checkpoint,cb_Early_Stop,cb_Reduce_LR]

What I would like is to see the training and validation loss on the screen after each batch and also record them in history.

halfer
  • 19,824
  • 17
  • 99
  • 186
user8270077
  • 4,621
  • 17
  • 75
  • 140
  • This feels rather broad currently, and appears to be a request for a section of work rather than help with a specific error or focused problem. Can you narrow it down at all? – halfer Nov 02 '19 at 11:12
  • Your last question was also too broad, and has garnered three close votes in that direction. – halfer Nov 02 '19 at 11:16
  • 1
    There is no need to add `Your advice will be appreciated` to the footer of all of your questions. You've probably had ~100 removed by now. Remember that the editors that try to keep this place tidy are volunteers. We may be foolish for taking on the task, but we believe in this community, for all its many faults. We would rather not have to clean up after users who add redundant and conversational material wilfully. – halfer Nov 03 '19 at 08:25

0 Answers0