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
Sparse4D (ResNet-101)
Model
NVIDIA
NVIDIA
Sparse4D (ResNet-101)

TAO Pretrained Sparse4D with ResNet-101 Backbone

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
Model Application(s):3D Multi-Camera Detection & Tracking of Objects
Describe the life-critical application (if present).This model performs 3D Detection & Tracking for multiple objects, including persons, humanoids, and autonomous mobile robots. This model may be used in the NVIDIA VSS release, for the purposes of providing real time alerts for events such as potential safety violations and security breaches, identifying on-demand insights pertaining to space and asset utilization, and ensuring the continuous integration of data for process optimization and strategic planning.
Use Case Restrictions:GOVERNING TERMS: Use of this model is governed by the NVIDIA Open Model License.
Describe access restrictions (if any):The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.