correct tutorial on fake loss (#862)

martinoywa · holly1238 · web-flow · commit 3708a180144c · 2021-04-24T11:26:54.000-07:00
Co-authored-by: holly1238 &lt;77758406+holly1238@users.noreply.github.com&gt;
diff --git a/beginner_source/dcgan_faces_tutorial.py b/beginner_source/dcgan_faces_tutorial.py
@@ -71,7 +71,7 @@
 # :math:`D` and :math:`G` play a minimax game in which :math:`D` tries to
 # maximize the probability it correctly classifies reals and fakes
 # (:math:`logD(x)`), and :math:`G` tries to minimize the probability that
-# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
+# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(z)))`).
 # From the paper, the GAN loss function is
 # 
 # .. math:: \underset{G}{\text{min}} \underset{D}{\text{max}}V(D,G) = \mathbb{E}_{x\sim p_{data}(x)}\big[logD(x)\big] + \mathbb{E}_{z\sim p_{z}(z)}\big[log(1-D(G(z)))\big]

Original file line number	Diff line number	Diff line change
`@@ -71,7 +71,7 @@`
`71`	`71`	# :math:`D` and :math:`G` play a minimax game in which :math:`D` tries to
`72`	`72`	`# maximize the probability it correctly classifies reals and fakes`
`73`	`73`	# (:math:`logD(x)`), and :math:`G` tries to minimize the probability that
`74`		-# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
	`74`	+# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(z)))`).
`75`	`75`	`# From the paper, the GAN loss function is`
`76`	`76`	`#`
`77`	`77`	`# .. math:: \underset{G}{\text{min}} \underset{D}{\text{max}}V(D,G) = \mathbb{E}_{x\sim p_{data}(x)}\big[logD(x)\big] + \mathbb{E}_{z\sim p_{z}(z)}\big[log(1-D(G(z)))\big]`