{ }
Computes the gradients of convolution with respect to the input.
tf.raw_ops.Conv2DBackpropInput(
input_sizes,
filter,
out_backprop,
strides,
padding,
use_cudnn_on_gpu=True,
explicit_paddings=[],
data_format='NHWC',
dilations=[1, 1, 1, 1],
name=None
)
Returns | |
---|---|
A Tensor . Has the same type as filter .
|