Conv2DBackpropFilter

tensorflow C++ API

Computes the gradients of convolution with respect to the filter.

Arguments:

scope: A Scope object
input: 4-D with shape[batch, in_height, in_width, in_channels].
filter_sizes: An integer vector representing the tensor shape offilter, wherefilteris a 4-D[filter_height, ilter_width, in_channels, out_channels]tensor.
out_backprop: 4-D with shape[batch, out_height, out_width, out_channels]. Gradients w.r.t. the output of the convolution.
strides: The stride of the sliding window for each dimension of the input of the convolution. Must be in the same order as the dimension specified with format.
padding: The type of padding algorithm to use.

Optional attributes (seeAttrs):

data_format: Specify the data format of the input and output data. With the default format "NHWC", the data is stored in the order of: [batch, in_height, in_width, in_channels]. Alternatively, the format could be "NCHW", the data storage order of: [batch, in_channels, in_height, in_width].

Returns:

Output: 4-D with shape[filter_height, filter_width, in_channels, out_channels]. Gradient w.r.t. thefilterinput of the convolution.

Argument:

Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
Input input: connect Input node.
Input filter_sizes: connect Input node.
Input out_backprop: connect Input node.
gtl::ArraySlice< int > strides: Input strides in value ex)1,2,2,1
StringPiece padding: Input paddingin value ex)SAME
Conv2DBackpropFilter ::Attrs attrs : Input attrs in value. ex) use_cudnn_on_gpu_ = true;data_format_ = NHWC;

Return:

Result:

std::vector(Tensor) result_output : Returned object of executed result by calling session.