From 950a698276377a2431ec14e192fbc2c60efd5210 Mon Sep 17 00:00:00 2001 From: MLRichter Date: Sun, 23 Jan 2022 23:56:17 +0100 Subject: [PATCH] fix: quality of life for coercing torch.nn.functional problems --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 93022b5..13af3bf 100644 --- a/README.md +++ b/README.md @@ -208,7 +208,7 @@ convolutional kernel. Here is a simple, 1-dimensional example: ![rf.PNG](https://github.com/MLRichter/receptive_field_analysis_toolbox/blob/main/images/rf.PNG?raw=true) The first layer of this simple architecture can only ever "see" the information the input pixels directly -under it's kernel, in this scenario 3 pixels. +under its kernel, in this scenario 3 pixels. Another observation we can make from this example is that the receptive field size is expanding from layer to layer. This is happening, because the consecutive layers also have kernel sizes greater than 1 pixel, which means that they combine multiple adjacent positions on the feature map into a single position in their output.