Correlation Cost Layer.
layer_correlation_cost(
object,
kernel_size,
max_displacement,
stride_1,
stride_2,
pad,
data_format,
...
)Model or layer object
An integer specifying the height and width of the patch used to compute the per-patch costs.
An integer specifying the maximum search radius for each position.
An integer specifying the stride length in the input.
An integer specifying the stride length in the patch.
An integer specifying the paddings in height and width.
Specifies the data format. Possible values are: "channels_last" float [batch, height, width, channels] "channels_first" float [batch, channels, height, width] Defaults to "channels_last".
additional parameters to pass
A tensor
This layer implements the correlation operation from FlowNet Learning Optical Flow with Convolutional Networks (Fischer et al.): https://arxiv.org/abs/1504.06