tf.nn.depthwise_conv2d_backprop_input

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

input_sizes A Tensor of type int32. An integer vector representing the shape of input, based on data_format. For example, if data_format is 'NHWC' then input is a 4-D [batch, height, width, channels] tensor.
filter A Tensor. Must be one of the following types: half, bfloat16, float32, float64. 4-D with shape [filter_height, filter_width, in_channels, depthwise_multiplier].
out_backprop A Tensor. Must have the same type as filter. 4-D with shape based on data_format. For example, if data_format is 'NHWC' then out_backprop shape is