ResNet34

class ResNet34(inputShape: IntArray?) : TFModels.CV<Functional>

This model is a neural network for image classification that take images as input and classify the major object in the image into a set of 1000 different classes (labels are available via org.jetbrains.kotlinx.dl.impl.dataset.Imagenet.V1k.labels method).

This model has 34 layers with ResNetv1 architecture.

The model have

an input with the shape (1x224x224x3)
an output with the shape (1x1000)

NOTE: ResNet v2 uses pre-activation function whereas ResNet v1 uses post-activation for the residual blocks.

See also

Deep Residual Learning for Image Recognition (CVPR 2015)

Constructors

ResNet34

fun ResNet34(inputShape: IntArray? = null)

Functions

loadModelConfiguration

open override fun loadModelConfiguration(jsonFile: File): Functional

Loads model configuration from the provided jsonFile.

model

open fun model(modelHub: ModelHub): Functional

pretrainedModel

open override fun pretrainedModel(modelHub: ModelHub): ImageRecognitionModel

Properties

inputShape

var inputShape: IntArray?

modelRelativePath

open override val modelRelativePath: String

preprocessor

open override val preprocessor: Operation<Pair<FloatArray, TensorShape>, Pair<FloatArray, TensorShape>>