MobilenetV1

object MobilenetV1 : ONNXModels.CV
Content copied to clipboard

Image classification model based on MobileNetV1 architecture. Trained on ImageNet 1k dataset. (labels are available via org.jetbrains.kotlinx.dl.impl.dataset.Imagenet.labels method).

MobileNetV1 is small, low-latency, low-power model and can be run efficiently on mobile devices

The model have

  • an input with the shape (1x224x224x3)

  • an output with the shape (1x1001)

See also

Functions

model
Link copied to clipboard
open fun model(modelHub: ModelHub): OnnxInferenceModel
Content copied to clipboard
pretrainedModel
Link copied to clipboard
open override fun pretrainedModel(modelHub: ModelHub): ImageRecognitionModel
Content copied to clipboard

Properties

inputShape
Link copied to clipboard
open val inputShape: LongArray?
Content copied to clipboard

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

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