MaxPoolGradGradWithArgmax

tensorflow C++ API

tensorflow::ops::MaxPoolGradGradWithArgmax

Computes second-order gradients of the maxpooling function.

Summary

Arguments:

• scope: A Scope object
• input: The original input.
• grad: 4-D with shape[batch, height, width, channels]. Gradients w.r.t. the input ofmax_pool.
• argmax: The indices of the maximum values chosen for each output ofmax_pool.
• ksize: The size of the window for each dimension of the input tensor.
• strides: The stride of the sliding window for each dimension of the input tensor.
• padding: The type of padding algorithm to use.

Returns:

• Output: Gradients of gradients w.r.t. the input ofmax_pool.

MaxPoolGradGradWithArgmax block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_nn.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input orig_input: connect Input node.
• Input grad: connect Input node.
• Input argmax: connect Input node.
• ArraySlice< int> ksize: input ksize in values. ex)1,2,2,2,1
• ArraySlice< int> strides: input ksize in values. ex)1,4,3,2,1
• stringpiece padding: input padding in value. ex)SAME

Return:

• Output output: Output object of MaxPoolGradGradWithArgmax class object.

Result:

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

Using Method