From 8d997db49b717f949ce63f82c4a90f93f67987b7 Mon Sep 17 00:00:00 2001 From: Bender Date: Wed, 9 Dec 2020 15:27:27 +0300 Subject: [PATCH] fix markdown (#4265) --- docs/tutorials/customize_runtime.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/tutorials/customize_runtime.md b/docs/tutorials/customize_runtime.md index 87653e18e..3f52b2732 100644 --- a/docs/tutorials/customize_runtime.md +++ b/docs/tutorials/customize_runtime.md @@ -180,7 +180,7 @@ so that 1 epoch for training and 1 epoch for validation will be run iteratively. 1. The parameters of model will not be updated during val epoch. 2. Keyword `total_epochs` in the config only controls the number of training epochs and will not affect the validation workflow. -3. Workflows `[('train', 1), ('val', 1)]` and `[('train', 1)]` will not change the behavior of `EvalHook` because `EvalHook` is called by `after_train_epoch` and validation workflow only affect hooks that are called through `after_val_epoch`. Therefore, the only difference between `[('train', 1), ('val', 1)]` and ``[('train', 1)]` is that the runner will calculate losses on validation set after each training epoch. +3. Workflows `[('train', 1), ('val', 1)]` and `[('train', 1)]` will not change the behavior of `EvalHook` because `EvalHook` is called by `after_train_epoch` and validation workflow only affect hooks that are called through `after_val_epoch`. Therefore, the only difference between `[('train', 1), ('val', 1)]` and `[('train', 1)]` is that the runner will calculate losses on validation set after each training epoch. ## Customize hooks