Enum ObjectDetectionImageSegmentation

pub enum ObjectDetectionImageSegmentation {
    TinyYoloV2,
    Ssd,
    SSDMobileNetV1,
    FasterRcnn,
    MaskRcnn,
    RetinaNet,
    YoloV2,
    YoloV2Coco,
    YoloV3,
    TinyYoloV3,
    YoloV4,
    Duc,
}

Object Detection & Image Segmentation

Object detection models detect the presence of multiple objects in an image and segment out areas of the image where the objects are detected. Semantic segmentation models partition an input image by labeling each pixel into a set of pre-defined categories.

Source: https://github.com/onnx/models#object_detection

Variants

TinyYoloV2

A real-time CNN for object detection that detects 20 different classes. A smaller version of the more complex full YOLOv2 network.

Variant downloaded: ONNX Version 1.3 with Opset Version 8.

Ssd

Single Stage Detector: real-time CNN for object detection that detects 80 different classes.

Variant downloaded: ONNX Version 1.5 with Opset Version 10.

SSDMobileNetV1

A variant of MobileNet that uses the Single Shot Detector (SSD) model framework. The model detects 80 different object classes and locates up to 10 objects in an image.

Variant downloaded: ONNX Version 1.7.0 with Opset Version 10.

FasterRcnn

Increases efficiency from R-CNN by connecting a RPN with a CNN to create a single, unified network for object detection that detects 80 different classes.

Variant downloaded: ONNX Version 1.5 with Opset Version 10.

MaskRcnn

A real-time neural network for object instance segmentation that detects 80 different classes. Extends Faster R-CNN as each of the 300 elected ROIs go through 3 parallel branches of the network: label prediction, bounding box prediction and mask prediction.

Variant downloaded: ONNX Version 1.5 with Opset Version 10.

RetinaNet

A real-time dense detector network for object detection that addresses class imbalance through Focal Loss. RetinaNet is able to match the speed of previous one-stage detectors and defines the state-of-the-art in two-stage detectors (surpassing R-CNN).

Variant downloaded: ONNX Version 1.6.0 with Opset Version 9.

YoloV2

A CNN model for real-time object detection system that can detect over 9000 object categories. It uses a single network evaluation, enabling it to be more than 1000x faster than R-CNN and 100x faster than Faster R-CNN.

Variant downloaded: ONNX Version 1.3 with Opset Version 8.

YoloV2Coco

A CNN model for real-time object detection system that can detect over 9000 object categories. It uses a single network evaluation, enabling it to be more than 1000x faster than R-CNN and 100x faster than Faster R-CNN. This model is trained with COCO dataset and contains 80 classes.

Variant downloaded: ONNX Version 1.5 with Opset Version 9.

YoloV3

A deep CNN model for real-time object detection that detects 80 different classes. A little bigger than YOLOv2 but still very fast. As accurate as SSD but 3 times faster.

Variant downloaded: ONNX Version 1.5 with Opset Version 10.

TinyYoloV3

A smaller version of YOLOv3 model.

Variant downloaded: ONNX Version 1.6 with Opset Version 11.

YoloV4

Optimizes the speed and accuracy of object detection. Two times faster than EfficientDet. It improves YOLOv3’s AP and FPS by 10% and 12%, respectively, with mAP50 of 52.32 on the COCO 2017 dataset and FPS of 41.7 on Tesla 100.

Variant downloaded: ONNX Version 1.6 with Opset Version 11.

Duc

Deep CNN based pixel-wise semantic segmentation model with >80% mIOU (mean Intersection Over Union). Trained on cityscapes dataset, which can be effectively implemented in self driving vehicle systems.

Variant downloaded: ONNX Version 1.2.2 with Opset Version 7.

Trait Implementations

impl Clone for ObjectDetectionImageSegmentation

fn clone(&self) -> ObjectDetectionImageSegmentation

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ObjectDetectionImageSegmentation

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl From<ObjectDetectionImageSegmentation> for AvailableOnnxModel

fn from(model: ObjectDetectionImageSegmentation) -> Self

Converts to this type from the input type.