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
TrafficCamNet Transformer Lite
Model
NVIDIA
NVIDIA
TrafficCamNet Transformer Lite

4 class object detection model for traffic intersections

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):Detecting Objects
Model Type:Convolutional Neural Network + Transformer Encoder Decoder
Intended Users:The model is intended for developers that build computer vision applications to detect cars, road signs, persons or two-wheelers in a video.
Output:Bounding Box, Class Labels
Describe how the model works:Extracts features from provided images for the car, persons, two-wheelers and road-signs.
Technical Limitations:The model may not perform well in low-light and low contrast video sequences and not detect cars that are more than 80% occluded.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Mean Average Precision (mAP)
Licensing:NVIDIA Open Model License
Potential Known Risks:The model may not not detect objects that are more than 80% occluded.