A convolution kernel that convolves the input image with a set of filters, with each producing one feature map in the output image.
SDKs
Framework
@interface MPSCNNConvolution : MPSCNNKernel
The attributes of a convolution operation are described by an MPSCNNConvolution object.
inputThe number of feature channels per pixel in the input image.
outputThe number of feature channels per pixel in the output image.
groupsThe number of groups that the input and output channels are divided into.
neuronThe neuron filter to be applied as part of the convolution operation.
MPSCNNNeuronA filter that applies a neuron activation function.
neuronDeprecatedMPSCNNNeuronThe types of neuron filter to append to a convolution.
neuronDeprecatedneuronDeprecatedneuronDeprecated- reloadDeprecatedMPSCNNBinaryA convolution kernel with binary weights and an input image using binary approximations.
MPSCNNDepthA description of a convolution object that does depthwise convolution.
MPSCNNSubA description of a convolution object that does subpixel upsampling and reshaping.
MPSCNNConvolutionA transposed convolution kernel.
MPSCNNConvolutionA gradient convolution kernel.
MPSCNNConvolutionAn object that exposes a gradient convolution kernel's gradient with respect to weights and biases.
MPSImageA protocol for objects that contain information about an image size elsewhere in the graph.
MPSCNNConvolutionA class that stores weights and biases.