From 8ebc0091f5eee1310b9439faabbd2968ccd3f779 Mon Sep 17 00:00:00 2001 From: Joshua Date: Tue, 28 May 2019 21:49:38 -0700 Subject: [PATCH] Corrected textual description of nueral style transfer loss function. --- 8.3-neural-style-transfer.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/8.3-neural-style-transfer.ipynb b/8.3-neural-style-transfer.ipynb index 72972f5f44..30fe0270f1 100644 --- a/8.3-neural-style-transfer.ipynb +++ b/8.3-neural-style-transfer.ipynb @@ -98,7 +98,7 @@ "\"content\", and `style` is a function that takes an image and computes a representation of its \"style\".\n", "\n", "Minimizing this loss would cause `style(generated_image)` to be close to `style(reference_image)`, while `content(generated_image)` would \n", - "be close to `content(generated_image)`, thus achieving style transfer as we defined it.\n", + "be close to `content(original_image)`, thus achieving style transfer as we defined it.\n", "\n", "A fundamental observation made by Gatys et al is that deep convolutional neural networks offer precisely a way to mathematically defined \n", "the `style` and `content` functions. Let's see how."