ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
—
PeopleSegNet
Model
—
PeopleSegNet

1 class instance segmentation network to detect and segment instances of people in an image.

NVIDIA AI Enterprise Supported
This model is backed by NVIDIA's Plus Plus (++) Promise
to learn more about the quality of the datasets used to train this model.
FieldResponse
Intended Application(s) & Domain(s):Segmenting people in smart spaces, retail, industrial applications.
Model Type:Instance segmentation
Intended Users:Developers working in smart spaces, retail, and industrial applications with people.
Output:Bounding Box(es), Category Label(s), Confidence Score(s)
Describe how the model works:Detects and labels bags, faces, and persons within an image and returns bounding box coordinates, labels, and confidence scores for each category.
Technical Limitations:Model should not be used in low-light, low contrast lighting conditions, with warped or motion-induced images, or very small and very large objects. Model accuracy may vary with occlusion or truncation.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Accuracy, Intersection over Union(IoU), Precision, Recall
Potential Known Risks:This model may fail to properly detect people.
Licensing:https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/