We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 7e51fa0 commit d13664eCopy full SHA for d13664e
beginner_source/dcgan_faces_tutorial.py
@@ -53,7 +53,7 @@
53
# :math:`D(x)` is the discriminator network which outputs the (scalar)
54
# probability that :math:`x` came from training data rather than the
55
# generator. Here, since we are dealing with images the input to
56
-# :math:`D(x)` is an image of HWC size 3x64x64. Intuitively, :math:`D(x)`
+# :math:`D(x)` is an image of CHW size 3x64x64. Intuitively, :math:`D(x)`
57
# should be HIGH when :math:`x` comes from training data and LOW when
58
# :math:`x` comes from the generator. :math:`D(x)` can also be thought of
59
# as a traditional binary classifier.
0 commit comments