loss

bayesflow.diagnostics.loss(history: History, train_key: str = 'loss', val_key: str = 'val_loss', moving_average: bool = False, per_training_step: bool = False, ma_window_fraction: float = 0.01, figsize: Sequence[float] = None, train_color: str = '#132a70', val_color: str = 'black', lw_train: float = 2.0, lw_val: float = 3.0, legend_fontsize: int = 14, label_fontsize: int = 14, title_fontsize: int = 16) → Figure

A generic helper function to plot the losses of a series of training epochs and runs.

Parameters:

historykeras.src.callbacks.History

History object as returned by keras.Model.fit.

train_keystr, optional, default: “loss”

The training loss key to look for in the history

val_keystr, optional, default: “val_loss”

The validation loss key to look for in the history

moving_averagebool, optional, default: False

A flag for adding a moving average line of the train_losses.

per_training_stepbool, optional, default: False

A flag for making loss trajectory detailed (to training steps) rather than per epoch.

ma_window_fractionint, optional, default: 0.01

Window size for the moving average as a fraction of total training steps.

figsizetuple or None, optional, default: None

The figure size passed to the matplotlib constructor. Inferred if None

train_colorstr, optional, default: ‘#8f2727’

The color for the train loss trajectory

val_colorstr, optional, default: black

The color for the optional validation loss trajectory

lw_trainint, optional, default: 2

The linewidth for the training loss curve

lw_valint, optional, default: 3

The linewidth for the validation loss curve

legend_fontsizeint, optional, default: 14

The font size of the legend text

label_fontsizeint, optional, default: 14

The font size of the y-label text

title_fontsizeint, optional, default: 16

The font size of the title text

Returns:

fplt.Figure - the figure instance for optional saving

Raises:

AssertionError

If the number of columns in train_losses does not match the number of columns in val_losses.