From dc6d3a6316e83ca01d91c533db94676fdaf22368 Mon Sep 17 00:00:00 2001
From: Vignesh Singaravelu <143326541+usefulldivider@users.noreply.github.com>
Date: Thu, 13 Jun 2024 18:19:11 +0530
Subject: [PATCH] adding a note about torch.mean

dtype can be used to specify the type rather than using typecasting
---
 00_pytorch_fundamentals.ipynb | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/00_pytorch_fundamentals.ipynb b/00_pytorch_fundamentals.ipynb
index 17c5d9ef..b14b93b5 100644
--- a/00_pytorch_fundamentals.ipynb
+++ b/00_pytorch_fundamentals.ipynb
@@ -2099,6 +2099,8 @@
    "source": [
     "> **Note:** You may find some methods such as `torch.mean()` require tensors to be in `torch.float32` (the most common) or another specific datatype, otherwise the operation will fail. \n",
     "\n",
+    ".mean has an optional parameter called dtype which tells the desired data type of returned tensor and also casts the input tensor to the specified dtype."
+    "\n"
     "You can also do the same as above with `torch` methods."
    ]
   },