TensorMath.subpixelArgMax
FunctionApplies subpixelArgMax function to the inTensor, with the specified inShape and kernel size.
- Available on all platforms
Platform details: Snapchat, SPECS, Camera Kit Web, Camera Kit Mobile fully supported.
subpixelArgMax(
inTensor,inShape,outTensor,kernelSize):void
Applies subpixelArgMax function to the inTensor, with the specified inShape and kernel size. The result is put into outTensor.
If inShape = {width, height, channels}, then the shape of outTensor should be {1, 2, channels}.
Parameters
| Parameter | Type |
|---|---|
inTensor | Float32Array |
inShape | vec3 |
outTensor | Float32Array |
kernelSize | number |
Returns
void