tofighi / yolox

Object Detector Using Yolo

  • Public
  • 653 runs
  • T4
  • GitHub
  • License

Input

input_image
*file

Path to an image

string

Model name

Default: "yolox-s"

number
(minimum: 0, maximum: 1)

Confidence threshold: Only detections with confidence higher are kept

Default: 0.3

number
(minimum: 0, maximum: 1)

NMS threshold: NMS removes redundant detections. Detections with overlap percentage (IOU) above this threshold are consider redundant to each other and only one of them will be kept

Default: 0.3

integer

Resize image to this size

Default: 640

boolean

Return results in json format

Default: false

Output

img
Generated in

This output was created using a different version of the model, tofighi/yolox:800b3b41.

Run time and cost

This model costs approximately $0.0064 to run on Replicate, or 156 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 29 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Model description

Intended use

Ethical considerations

Caveats and recommendations