Skip to content

2 mistakes found #39

@owenliang

Description

@owenliang

in linearregression,

# Create a callback that saves the model's weights every 5 epochs
checkpointCallback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_path, 
    verbose=1, 
    save_weights_only=True,
    save_freq=n_samples_save)

save_freq should be number of epochs(not batches):

# Create a callback that saves the model's weights every 5 epochs
checkpointCallback = tf.keras.callbacks.ModelCheckpoint(
    filepath=checkpoint_path, 
    verbose=1, 
    save_weights_only=True,
    save_freq=n_epochs_log)
# Return unique list elements
checkpoints =list(set(checkpoints))
print('checkpoints:',checkpoints)

to make the figures understood, the checkpoints file list should be sorted by created order:

# Return unique list elements
checkpoints = sorted(list(set(checkpoints)))
print('checkpoints:',checkpoints)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions