ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
—
PeopleSemSegNet AMR
Model
—
PeopleSemSegNet AMR

Semantic segmentation of persons in an image.

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
Participation considerations from adversely impacted groups (protected classes) in model design and testing:Gender, Skin Color
Measures taken to mitigate against unwanted bias:Developed customized dataset that included video from persons of different skin colors in different geographic settings. Unwanted bias is mitigated by the collection of data in different urban areas at different times of the day during typical working hours and outside of typical working times to get a diversity of races and skin tones.