Predictions callbacks

Various callbacks to customize get_preds behaviors

MCDropoutCallback

Turns on dropout during inference, allowing you to call Learner.get_preds multiple times to approximate your model uncertainty using Monte Carlo Dropout.

---

source

MCDropoutCallback

def MCDropoutCallback(
    after_create:NoneType=None, before_fit:NoneType=None, before_epoch:NoneType=None, before_train:NoneType=None,
    before_batch:NoneType=None, after_pred:NoneType=None, after_loss:NoneType=None, before_backward:NoneType=None,
    after_cancel_backward:NoneType=None, after_backward:NoneType=None, before_step:NoneType=None,
    after_cancel_step:NoneType=None, after_step:NoneType=None, after_cancel_batch:NoneType=None,
    after_batch:NoneType=None, after_cancel_train:NoneType=None, after_train:NoneType=None,
    before_validate:NoneType=None, after_cancel_validate:NoneType=None, after_validate:NoneType=None,
    after_cancel_epoch:NoneType=None, after_epoch:NoneType=None, after_cancel_fit:NoneType=None,
    after_fit:NoneType=None
):

Basic class handling tweaks of the training loop by changing a Learner in various events

learn = synth_learner()

# Call get_preds 10 times, then stack the predictions, yielding a tensor with shape [# of samples, batch_size, ...]
dist_preds = []
for i in range(10):
    preds, targs = learn.get_preds(cbs=[MCDropoutCallback()])
    dist_preds += [preds]

torch.stack(dist_preds).shape

torch.Size([10, 32, 1])