Model

model

Model

fit(self, autodataset, epochs=1, steps_per_epoch=None, callbacks=None, resume=True, progress_kwargs=None)

Similar to Keras model.fit() it trains the model for specified epochs and returns Tracker object

Parameters:

Name	Type	Description	Default
autodataset	AutoDataset	AutoDataset object encapsulate dataloader and datamodule	required
epochs	int	number of epochs to train	1
steps_per_epoch	Optional[int]	Number of steps trained in a single epoch	None
callbacks	Optional[List]	Callback object or string	None
resume	bool	Resume training from the last epoch	True
progress_kwargs	Optional[Dict]	Arguments for rich.progress	None

Returns:

Type	Description
Tracker	Tracker object

tracker

Tracker

Tracks loss, accuracy and model weights during model.fit()

---

Last update: September 25, 2021