loop¶
Loop¶
- class Loop(model, optimizer, loss_fn, metrics=None, callbacks=(), history=None, device='cpu')¶
The simplest kind of loop for basic supervised learning.
Note
If you have more custom things you’d like to to that cant be handled in callbacks it’s recommended to subclass this and overide the
handle_batch
method.- stages = ('train', 'val')¶
- property optimizer¶
- to(device)¶
- property metrics¶
- property loss_fn¶
- property loss¶
- property metric¶
- grad_context()¶
- optimizer_step()¶
- compute_loss(yhat, ytru, **kwargs)¶
- compute_metric(yhat, ytru, **kwargs)¶
- backward(loss, **kwargs)¶
- forward(x, **kwargs)¶
- handle_batch(batch)¶
- handle_batches(batches)¶
- handle_stage(stage, batches)¶
- fire(event)¶