EfficientNetB3
class EfficientNetB3(noTop: Boolean) : ONNXModels.CV<OnnxInferenceModel>
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.api.core.util.loadImageNetClassLabels method).
Instantiates the EfficientNetB3 architecture.
The model have
an input with the shape (1x300x300x3)
an output with the shape (1x1000)
an output for noTop model with the shape (1x9x9x1536)
NOTE: This model is converted from Keras.applications, the last two layers in the noTop model have been removed so that the user can fine-tune the model for his specific task.
See also
Constructors
EfficientNetB3
Link copied to clipboard
Functions
model
Link copied to clipboard
preInit
Link copied to clipboard
preprocessInput
Link copied to clipboard
open fun preprocessInput(imageFile: File, preprocessing: Preprocessing): FloatArray
Content copied to clipboard
open override fun preprocessInput(data: FloatArray, tensorShape: LongArray): FloatArray
Content copied to clipboard
pretrainedModel
Link copied to clipboard
open override fun pretrainedModel(modelHub: ModelHub): ImageRecognitionModel
Content copied to clipboard