NASNetLarge

class NASNetLarge(noTop: Boolean, inputShape: IntArray?) : TFModels.CV<Functional>
Content copied to clipboard

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).

Instantiates the NASNetLarge architecture.

The model have

  • an input with the shape (1x224x224x3)

  • an output with the shape (1x1000)

NOTE: This model is converted from Keras.applications, the last few layers in the noTop model have been removed so that the user can fine-tune the model for his specific task.

See also

Constructors

NASNetLarge
Link copied to clipboard
fun NASNetLarge(noTop: Boolean = false, inputShape: IntArray? = intArrayOf(331, 331, 3))
Content copied to clipboard

Functions

loadModelConfiguration
Link copied to clipboard
open override fun loadModelConfiguration(jsonFile: File): Functional
Content copied to clipboard

Loads model configuration from the provided jsonFile.

model
Link copied to clipboard
open fun model(modelHub: ModelHub): Functional
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
var inputShape: IntArray?
Content copied to clipboard
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