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
NVIDIA
NVIDIA
CitySemSegFormer
Model
NVIDIA
NVIDIA
CitySemSegFormer

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
Intended Application(s) & Domain(s):Segmenting city scapes and and urban city classes.
Model Type:Semantic Segmentation
Intended Users:Developers working in geo-spatial and transportation applications.
Output:Segmentation Masks
Describe how the model works:Associates urban cityscapes label for each image pixel.
Technical Limitations:Model may not detect classes of persons (passengers, riders), trucks, trains, motorcycles, and other out-of-road elements found in intelligent transportation system datasets.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Accuracy, Mean Intersection over Union (IoU), Precision, Recall
Potential Known Risks:Inaccurate segmentation for navigation could lead to collisions.
Licensing:https://www.nvidia.com/en-us/data-center/products/nvidia-ai-enterprise/eula/