tensordecoders

Subpages:

classifiertensordecoder – Decode tensors output from classification model using common format. Tensor format must be: Dims: [batch-size, class_count] Datatype: float32

	Tensor [M,N]
		Batch 0   | Class 0 confidence level | ... | Class N-1 confidence level |
		...
		Batch M-1 | Class 0 confidence level | ... | Class N-1 confidence level |
	
In-memory tensor format:

	|Batch 0, Class 0 confidence level     |
	|Batch 0,           ...                |
	|Batch 0, Class N-1 confidence level   |
	|               ...                    |
	|Batch M-1, Class 0 confidence level   |
	|Batch M-1,           ...              |
	|Batch M-1, Class N-1 confidence level |

model

GstSsdTensorDec

GstYoloTensorDecoder

ioutracker – Track the objects across frames based on Intersection-over-Union (IoU)

ssdobjectdetector – Apply tensor output from inference to detect objects in video frames

ssdtensordec – Apply tensor output from inference to detect objects in video frames

tensordecodebin – Tensor Decode Bin

ultralightfacedetectortensordec – Detect tensor output from the inference of Ultra Light Face Detection to detect the faces in video frames.The original repository of the Ultra Light Face Detection is located at https://github.com/Linzaer/Ultra-Light-Fast-Generic-Face-Detector-1MB.

yolosegv8tensordec – Decode tensors output from the inference of Yolo or FastSAM model (segmentation) on video frames. It works with YOLO version > 8 and FastSAM models.

yolov8tensordec – Decode tensors output from the inference of YOLO Object Detection or FastSAM model (Detection)on video frames. This works on YOLO version 8 and later(v11), and FastSAM models.