Runs as a custom pluginDetectionVerified 2026-11-05
YOLOX-S
yolox_s (Megvii release asset)
YOLOX-S is a image object detection model (Apache-2.0). Can run on Mixpeek as a custom plugin.
Mixpeek does not run it today. It can run as a custom plugin: the weights load without remote code.
No demo for YOLOX-S yet
A video, image, slideshow or playground goes here once we record one on our own data.
What it is good and bad at
- Best at
- Mature Apache-2.0 YOLO-style detector with official ONNX exports; easy CPU deployment.
- Worst at
- Older (2021): lower accuracy than D-FINE or RT-DETRv2 at equal cost; closed COCO label set.
- Task
- Detection
- Input
- Image
- Output
- Boxes, Labels, Scores
- Use cases
- Object detection
Templates that use it
No template uses this model yet. Browse templates.
Input and output
Input
- image
- resolution
- 640x640 letterboxed
- color
- BGR, no normalization (reference demo)
- prompts
- none
Output
- boxes
- xyxy pixels after grid decode
- labels
- COCO 80 classes
- scores
- objectness x class
How Mixpeek wires it
- Extractors
- None today
- Feature URIs
- None today
- Vector indexes
- None
- Retriever stages
- None
- Combines with
- detector boxes -> crops -> SigLIP vectors per object (one document per object, or a multi-vector per frame)
- labels -> payload field -> attribute filter in a retriever
- scene splits -> keyframes -> detector -> object documents with frame timestamps
How it runs
- Status
- Runs as a custom plugin Not served. Would run as a custom extractor plugin with onnxruntime on CPU using the official yolox_s.onnx release asset (no Python model code needed).
- Serve apps
- None
- Runtime
- onnxruntime (official ONNX release)
- Weights
- ONNX, no remote code
- Parameters
- 9 M
- Size on disk
- Not recorded
- Preprocessing
- Letterbox to 640 with padding value 114.
- Postprocessing
- Decode grid outputs, score threshold, NMS.
- Serving
- both
- Hardware
- Runs on CPU (slower without a GPU)
Scale to zero
- Minimum replicas
- 0
- Maximum replicas
- 1
- Idle timeout
- 600 s
- Memory
- 1 GB
- CPUs
- 1
- GPUs
- 0
- Cold start, node warm
- Not recorded
- Cold start, new node
- Not recorded
Measured cost
Unmeasured
No committed measurement; plan row 3 measures it in the standalone image.
Our evaluations
Unmeasured
We have not evaluated this model on our own data yet. Publisher results are in the sources below.
Questions
- What is YOLOX-S best at?
- Mature Apache-2.0 YOLO-style detector with official ONNX exports; easy CPU deployment.
- What are the limits of YOLOX-S?
- Older (2021): lower accuracy than D-FINE or RT-DETRv2 at equal cost; closed COCO label set.
- Can YOLOX-S be used commercially?
- Yes. Apache-2.0 weights and code; no use restrictions.
- How does YOLOX-S run on Mixpeek?
- Not served. Would run as a custom extractor plugin with onnxruntime on CPU using the official yolox_s.onnx release asset (no Python model code needed).