diff options
Diffstat (limited to 'tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md')
-rw-r--r-- | tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md b/tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md index 5b2a0bb95b..e60a31ea5c 100644 --- a/tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md +++ b/tensorflow/g3doc/api_docs/python/functions_and_classes/shard4/tf.nn.conv2d_transpose.md @@ -11,9 +11,9 @@ deconvolution. * <b>`value`</b>: A 4-D `Tensor` of type `float` and shape - `[batch, height, width, in_channels]`. + `[batch, in_height, in_width, in_channels]`. * <b>`filter`</b>: A 4-D `Tensor` with the same type as `value` and shape - `[height, width, output_channels, in_channels]`. `filter`'s + `[filter_height, filter_width, output_channels, in_channels]`. `filter`'s `in_channels` dimension must match that of `value`. * <b>`output_shape`</b>: A 1-D `Tensor` representing the output shape of the deconvolution op. |