tf.nn.depthwise_conv2d_backprop_filter

Computes the gradients of depthwise convolution with respect to the filter.

input A Tensor. Must be one of the following types: half, bfloat16, float32, float64. 4-D with shape based on data_format. For example, if data_format is 'NHWC' then input is a 4-D [batch, in_height, in_width, in_channels] tensor.
filter_sizes A Tensor of type int32. An integer