{ }
View source on GitHub |
Computes the gradients of convolution with respect to the filter.
tf.compat.v1.nn.conv2d_backprop_filter(
input,
filter_sizes,
out_backprop,
strides,
padding,
use_cudnn_on_gpu=True,
data_format='NHWC',
dilations=[1, 1, 1, 1],
name=None
)
Returns | |
---|---|
A Tensor . Has the same type as input .
|