From 42da2a5a23ae40d6df65362d371629557296ac07 Mon Sep 17 00:00:00 2001 From: Eric Zelikman Date: Thu, 10 Dec 2020 12:51:43 -0500 Subject: [PATCH] not hosting any images on google drive --- C2W2_(Optional_Notebook)_Score_Based_Generative_Modeling.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/C2W2_(Optional_Notebook)_Score_Based_Generative_Modeling.ipynb b/C2W2_(Optional_Notebook)_Score_Based_Generative_Modeling.ipynb index 7acc52a..9ea2d61 100644 --- a/C2W2_(Optional_Notebook)_Score_Based_Generative_Modeling.ipynb +++ b/C2W2_(Optional_Notebook)_Score_Based_Generative_Modeling.ipynb @@ -16671,7 +16671,7 @@ "where $\\bar{\\mathbf{w}}$ is a Brownian motion in the reverse time direction, and $dt$ here represents an infinitesimal negative time step. Here $p_t(\\mathbf{x})$ represents the distribution of $\\mathbf{x}(t)$. This reverse SDE can be computed once we know the drift and diffusion coefficients of the forward SDE, as well as the score of $p_t(\\mathbf{x})$ for each $t\\in[0, T]$.\n", "\n", "The overall intuition of score-based generative modeling with SDEs can be summarized in the illustration below\n", - "![sde schematic](https://drive.google.com/uc?id=1cHHEE3Cfo82Oiir-fLlE1rmSmD5l1ay5)\n", + "![sde schematic](https://github.com/https-deeplearning-ai/GANs-Public/blob/master/diffusion_schematic.jpg?raw=true)\n", "\n", "### Score Estimation\n", "\n",