It should be log(1-D(G(z))) (#428)

vjayd · soumith · commit adc8187969d7 · 2019-03-28T00:52:05.000-04:00
Correction done from log(1-D(G(x))) to log(1-D(G(x))).
Please review
diff --git a/beginner_source/dcgan_faces_tutorial.py b/beginner_source/dcgan_faces_tutorial.py
@@ -74,7 +74,7 @@
 # :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
 # 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(x)))\big]
+# .. 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]
 # 
 # In theory, the solution to this minimax game is where
 # :math:`p_g = p_{data}`, and the discriminator guesses randomly if the

Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,7 @@`
`74`	`74`	# :math:`D` will predict its outputs are fake (:math:`log(1-D(G(x)))`).
`75`	`75`	`# From the paper, the GAN loss function is`
`76`	`76`	`#`
`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(x)))\big]`
	`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]`
`78`	`78`	`#`
`79`	`79`	`# In theory, the solution to this minimax game is where`
`80`	`80`	# :math:`p_g = p_{data}`, and the discriminator guesses randomly if the