PoseDetection

sealed class PoseDetection<U : InferenceModel> : OnnxModelType<U>

Pose detection models.

Types

MoveNetMultiPoseLighting
Link copied to clipboard

A convolutional neural network model that runs on RGB images and predicts human joint locations of people in the image frame. The main differentiator between this MoveNet.MultiPose and its precedent, MoveNet.SinglePose model, is that this model is able to detect multiple people in the image frame at the same time while still achieving real-time speed.

MoveNetSinglePoseLighting
Link copied to clipboard

This model is a convolutional neural network model that runs on RGB images and predicts human joint locations of a single person. (edges are available in org.jetbrains.kotlinx.dl.onnx.inference.posedetection.edgeKeyPointsPairs and keypoints are in org.jetbrains.kotlinx.dl.onnx.inference.posedetection.keyPoints).

MoveNetSinglePoseThunder
Link copied to clipboard

This model is a convolutional neural network model that runs on RGB images and predicts human joint locations of a single person. (edges are available in org.jetbrains.kotlinx.dl.onnx.inference.posedetection.edgeKeyPointsPairs and keypoints are in org.jetbrains.kotlinx.dl.onnx.inference.posedetection.keyPoints).

Functions

model
Link copied to clipboard
open fun model(modelHub: ModelHub): OnnxInferenceModel
pretrainedModel
Link copied to clipboard
abstract fun pretrainedModel(modelHub: ModelHub): U

Properties

inputShape
Link copied to clipboard
open val inputShape: LongArray?

Shape of the input accepted by this model, without batch size.

modelRelativePath
Link copied to clipboard
open override val modelRelativePath: String
preprocessor
Link copied to clipboard
open val preprocessor: Operation<Pair<FloatArray, TensorShape>, Pair<FloatArray, TensorShape>>

Inheritors

ONNXModels.PoseDetection
Link copied to clipboard
ONNXModels.PoseDetection
Link copied to clipboard
ONNXModels.PoseDetection
Link copied to clipboard