From d5e31872489483c8ba298247435864256e4eba43 Mon Sep 17 00:00:00 2001
From: afaytout <achraf.faytout@ecl22.ec-lyon.fr>
Date: Fri, 1 Dec 2023 15:24:50 +0100
Subject: [PATCH] Answer first question
explain the difference between the loss of train and validation.
---
TD2 Deep Learning.ipynb | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/TD2 Deep Learning.ipynb b/TD2 Deep Learning.ipynb
index abb507f..d5db02a 100644
--- a/TD2 Deep Learning.ipynb
+++ b/TD2 Deep Learning.ipynb
@@ -554,6 +554,14 @@
"Does overfit occur? If so, do an early stopping."
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<p><span style = \"color : orange;\">Answer :</span> Yes, Overfitting has been happening since the 15th epoch, the plot below show the increase of the loss.</p>\n",
+ "<p>we're talking about validation, because the train loss can't demonstrate if the model can generalize.</p>"
+ ]
+ },
{
"cell_type": "code",
"execution_count": 10,
--
GitLab