Skip to content

Commit 6d2519f

Browse files
authored
fix typo
1 parent 927f811 commit 6d2519f

File tree

1 file changed

+3
-3
lines changed
  • tensorflow/contrib/layers/python/layers

1 file changed

+3
-3
lines changed

tensorflow/contrib/layers/python/layers/layers.py

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -858,7 +858,7 @@ def convolution(inputs,
858858
with "NC".
859859
num_outputs: Integer, the number of output filters.
860860
kernel_size: A sequence of N positive integers specifying the spatial
861-
dimensions of of the filters. Can be a single integer to specify the same
861+
dimensions of the filters. Can be a single integer to specify the same
862862
value for all spatial dimensions.
863863
stride: A sequence of N positive integers specifying the stride at which to
864864
compute output. Can be a single integer to specify the same value for all
@@ -1097,7 +1097,7 @@ def convolution2d_transpose(
10971097
`[batch, height, width, in_channels]` for `NHWC` data format or
10981098
`[batch, in_channels, height, width]` for `NCHW` data format.
10991099
num_outputs: Integer, the number of output filters.
1100-
kernel_size: A list of length 2 holding the [kernel_height, kernel_width] of
1100+
kernel_size: A list of length 2 holding the [kernel_height, kernel_width]
11011101
of the filters. Can be an int if both values are the same.
11021102
stride: A list of length 2: [stride_height, stride_width].
11031103
Can be an int if both strides are the same. Note that presently
@@ -1858,7 +1858,7 @@ def separable_convolution2d(
18581858
inputs: A tensor of size [batch_size, height, width, channels].
18591859
num_outputs: The number of pointwise convolution output filters. If is
18601860
None, then we skip the pointwise convolution stage.
1861-
kernel_size: A list of length 2: [kernel_height, kernel_width] of
1861+
kernel_size: A list of length 2: [kernel_height, kernel_width]
18621862
of the filters. Can be an int if both values are the same.
18631863
depth_multiplier: The number of depthwise convolution output channels for
18641864
each input channel. The total number of depthwise convolution output

0 commit comments

Comments
 (0)