From f353b021b56b09b5397c6276f36f40d46fe22133 Mon Sep 17 00:00:00 2001 From: William Falcon Date: Thu, 16 Jan 2020 10:51:15 -0500 Subject: [PATCH] working on trainer docs --- pytorch_lightning/trainer/trainer.py | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/pytorch_lightning/trainer/trainer.py b/pytorch_lightning/trainer/trainer.py index 8e932e37..565754f4 100644 --- a/pytorch_lightning/trainer/trainer.py +++ b/pytorch_lightning/trainer/trainer.py @@ -396,10 +396,8 @@ class Trainer(TrainerIOMixin, truncated_bptt_steps (int): Truncated back prop breaks performs backprop every k steps of a much longer sequence If this is enabled, your batches will automatically get truncated and the trainer will apply Truncated Backprop to it. Make sure your batches have a sequence dimension. - `Williams, Ronald J., and Jing Peng. "An efficient gradient-based algorithm for on-line training of recurrent network trajectories." - `_ - - + (`Williams et al. "An efficient gradient-based algorithm for on-line training of recurrent network trajectories." + `_) Example:: # default used by the Trainer (ie: disabled) trainer = Trainer(truncated_bptt_steps=None)