jarvissan22/yolo_tracker

Public
5 runs

Run jarvissan22/yolo_tracker with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field Type Default value Description
video
string
Input video file (MP4 / AVI / MOV).
model_weights
string
yolo11m.pt
YOLO weights. Named model ('yolo11m.pt'), HTTPS URL, s3:// URI, or absolute container path.
tracker_config
None
bytetrack.yaml
YOLO tracker config.
conf
number
0.2

Min: 0.01

Max: 1

Detection confidence threshold.
iou
number
0.7

Min: 0.01

Max: 1

IoU threshold for NMS.
max_det
integer
600

Min: 1

Max: 3000

Maximum detections per frame.
max_frames
integer
1000
Cap on frames to process (0 = no cap).
color_palette
string
[[255, 0, 0], [0, 0, 255], [0, 255, 0], [0, 255, 255], [0, 128, 255], [128, 0, 128], [255, 0, 255], [0, 255, 128], [255, 255, 0], [128, 128, 0], [255, 128, 0], [128, 0, 0], [0, 128, 0], [0, 0, 128], [128, 128, 128], [255, 255, 255], [128, 128, 255], [255, 128, 255], [128, 255, 128], [255, 255, 128], [128, 255, 255]]
JSON array of [R, G, B] colours used to draw bounding boxes. Colour is chosen by class_id %% len(palette). Example: '[[255,0,0],[0,255,0],[0,0,255]]'
box_thickness
integer
2

Min: 1

Max: 10

Thickness (px) of bounding-box rectangle lines.
jpeg_quality
integer
75

Min: 1

Max: 100

JPEG quality for annotated frame thumbnails (1–100). Lower = smaller payload, faster streaming.

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{
  "type": "array",
  "items": {
    "type": "string"
  },
  "title": "Output",
  "x-cog-array-type": "iterator"
}