CV

sealed class CV<T : GraphTrainableModel> : ModelType<T, ImageRecognitionModel>

Image recognition models and preprocessing.

Types

DenseNet121
Link copied to clipboard
class DenseNet121(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.api.core.util.loadImageNetClassLabels method).

DenseNet169
Link copied to clipboard
class DenseNet169(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.api.core.util.loadImageNetClassLabels method).

DenseNet201
Link copied to clipboard
class DenseNet201(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.api.core.util.loadImageNetClassLabels method).

Inception
Link copied to clipboard
class Inception(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

MobileNet
Link copied to clipboard
class MobileNet(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

MobileNetV2
Link copied to clipboard
class MobileNetV2(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

NASNetLarge
Link copied to clipboard
class NASNetLarge(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

NASNetMobile
Link copied to clipboard
class NASNetMobile(noTop: Boolean) : 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.api.core.util.loadImageNetClassLabels method).

ResNet101
Link copied to clipboard
class ResNet101(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

ResNet101v2
Link copied to clipboard
class ResNet101v2(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

ResNet152
Link copied to clipboard
class ResNet152(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

ResNet152v2
Link copied to clipboard
class ResNet152v2(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

ResNet18
Link copied to clipboard
class ResNet18(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.api.core.util.loadImageNetClassLabels method).

ResNet34
Link copied to clipboard
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.api.core.util.loadImageNetClassLabels method).

ResNet50
Link copied to clipboard
class ResNet50(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

ResNet50v2
Link copied to clipboard
class ResNet50v2(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

VGG16
Link copied to clipboard
class VGG16(noTop: Boolean, inputShape: IntArray?) : TFModels.CV<Sequential>

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.api.core.util.loadImageNetClassLabels method).

VGG19
Link copied to clipboard
class VGG19(noTop: Boolean, inputShape: IntArray?) : TFModels.CV<Sequential>

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.api.core.util.loadImageNetClassLabels method).

Xception
Link copied to clipboard
class Xception(noTop: Boolean, 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.api.core.util.loadImageNetClassLabels method).

Functions

model
Link copied to clipboard
open fun model(modelHub: ModelHub): T

Loads the model, identified by this name, from the modelHub.

preInit
Link copied to clipboard
open fun preInit(): InferenceModel
preprocessInput
Link copied to clipboard
open fun preprocessInput(imageFile: File, preprocessing: Preprocessing): FloatArray
abstract fun preprocessInput(data: FloatArray, tensorShape: LongArray): FloatArray

Common preprocessing function for the Neural Networks trained on ImageNet and whose weights are available with the keras.application.

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

Returns the specially prepared pre-trained model of the type U.

Properties

channelsFirst
Link copied to clipboard
open override val channelsFirst: Boolean = false

If true it means that the second dimension is related to number of channels in image has short notation as NCWH, otherwise, channels are at the last position and has a short notation as NHWC.

inputShape
Link copied to clipboard
var inputShape: IntArray? = null
modelRelativePath
Link copied to clipboard
open override val modelRelativePath: String

Relative path to model for local and S3 buckets storages.

Inheritors

TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard
TFModels.CV
Link copied to clipboard