Class Conv3d
java.lang.Object
ai.beestream.jitnn.nn.Module
ai.beestream.jitnn.nn.Conv3d
- All Implemented Interfaces:
AutoCloseable
3-D convolution over [N, C, ...] with a cubic kernel, optionally grouped, PyTorch's initialisation:
weight and bias uniform in [-1/sqrt(fan_in), 1/sqrt(fan_in)), fan_in = in * kernel^3.
-
Constructor Summary
ConstructorsConstructorDescriptionConv3d(int in, int out, int kernel, int stride, int padding, int dilation, boolean bias, long seed) A 3-D convolution fromintooutchannels with a cubic kernel, initialised fromseed.Conv3d(int in, int out, int kernel, int stride, int padding, int dilation, int groups, boolean bias, long seed) Withgroupsgroups of in / groups input channels each (fan_in = in / groups * kernel^3). -
Method Summary
Methods inherited from class Module
buffer, buffers, child, close, isClosed, isTraining, loadStateDict, parameter, parameterCount, parameters, stateDict, train, zeroGrad
-
Constructor Details
-
Conv3d
public Conv3d(int in, int out, int kernel, int stride, int padding, int dilation, boolean bias, long seed) A 3-D convolution fromintooutchannels with a cubic kernel, initialised fromseed. -
Conv3d
public Conv3d(int in, int out, int kernel, int stride, int padding, int dilation, int groups, boolean bias, long seed) Withgroupsgroups of in / groups input channels each (fan_in = in / groups * kernel^3).
-
-
Method Details
-
weight
The weight [out, in, kernel, kernel, kernel]. -
forward
-