YoloV4Classifier

open class YoloV4Classifier : Classifier

Wrapper for frozen detection models trained using the Tensorflow Object Detection API: - https://github.com/tensorflow/models/tree/master/research/object_detection where you can find the training code.

To use pretrained models in the API or convert to TF Lite models, please see docs for details: - https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md - https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/running_on_mobile_tensorflowlite.md#running-our-model-on-android

Functions

Link copied to clipboard
open fun checkInvalidateBox(    x: Float,     y: Float,     width: Float,     height: Float,     oriW: Float,     oriH: Float,     intputSize: Int): Boolean
Link copied to clipboard
open fun close()
Link copied to clipboard
open fun create(    assetManager: AssetManager,     modelFile: File,     labelFilename: String,     isQuantized: Boolean): Classifier

open fun create(    assetManager: AssetManager,     modelFilename: String,     labelFilename: String,     isQuantized: Boolean): Classifier
Initializes a native TensorFlow session for classifying images.
Link copied to clipboard
open fun enableStatLogging(logStats: Boolean)
Link copied to clipboard
open fun getObjThresh(): Float
Link copied to clipboard
open fun getStatString(): String
Link copied to clipboard
open fun recognizeImage(bitmap: Bitmap): ArrayList<Classifier.Recognition>
Link copied to clipboard
open fun setNumThreads(num_threads: Int)
Link copied to clipboard
open fun setUseNNAPI(isChecked: Boolean)