We need your help! 🔥
Please consider disabling your ad-blocker to support this website! 🔑
We are a free, community-supported website! 🥰
We only display small unobtrusive ads which help us stay online! 💯
Thank you in advance! ❤️
We are a free, community-supported website! 🥰
We only display small unobtrusive ads which help us stay online! 💯
Thank you in advance! ❤️
Object Detection Using ONNX File
Use a pre-trained deep learning Open Neural Network Exchange (ONNX) file for object detection and 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. For more information visit http://https://onnx.ai/
Inputs
| Name | ID | Description | Type |
|---|---|---|---|
| Bitmap Path | Bmp | The full path to a image file. | Text |
| Model Path | Model | The file path to the pre-trained ONNX Model. This component works with the YOLO (You Only Look Once) V4 model which can be downloaded at https://github.com/onnx/models/tree/master/vision/object_detection_segmentation/yolov4. The YOLO V4 model is a pre-trained deep convolutional neural network for real-time object detection that detects 80 different classes. | Text |
Outputs
| Name | ID | Description | Type |
|---|---|---|---|
| Bitmap with Regions | Bmp | The bitmap with bounding boxes drawn on the image. | Generic |
| Image Boundary | Boundary | A rectangle representing the boundary of the image.The boundary has been normalized such that the maximum dimension of the image (ie. width or height) fall within the [0-1] domain. | Rectangle |
| Image Regions | Regions | Rectangles regions representing classified areas of interest in the image. The rectangles have been normalized such that the maximum dimension of the image (ie. width or height) fall within the [0-1] domain. | Rectangle |
| Statistics | Stats | Statistics for the image classification. | Generic |
Site design © Robin Rodricks.
LunchBox and associated data © 2024 Nathan Miller.
Rhinoceros and Grasshopper are registered trademarks of Robert McNeel & Associates.
Hosted by GitHub