From 909fbd19eaee0080c12bdc0f069121ee1d006907 Mon Sep 17 00:00:00 2001 From: Francois Chollet Date: Mon, 12 Dec 2016 15:56:56 -0800 Subject: [PATCH] Update answer to validation split Q in FAQ --- docs/templates/getting-started/faq.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/templates/getting-started/faq.md b/docs/templates/getting-started/faq.md index 88e00bf51..099dbdcbc 100644 --- a/docs/templates/getting-started/faq.md +++ b/docs/templates/getting-started/faq.md @@ -226,8 +226,9 @@ Find out more in the [callbacks documentation](/callbacks). ### How is the validation split computed? -If you set the `validation_split` argument in `model.fit` to e.g. 0.1, then the validation data used will be the *last 10%* of the data. If you set it to 0.25, it will be the last 25% of the data, etc. +If you set the `validation_split` argument in `model.fit` to e.g. 0.1, then the validation data used will be the *last 10%* of the data. If you set it to 0.25, it will be the last 25% of the data, etc. Note that the data isn't shuffled before extracting the validation split, so the validation is literally just the *last* x% of samples in the input you passed. +The same validation set is used for all epochs (within a same call to `fit`). ---