Skip to main content
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
    TAO Pretrained Object Detection
    Model
    NVIDIA
    TAO Pretrained Object Detection

    Pretrained weights to facilitate transfer learning using TAO Toolkit.

  • 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):General-purpose object detection (weights are dataset dependent)
    Model Type:Object Detection
    Intended Users:Industrial and retail developers building including those for safety and security applications.
    Output:Bounding Box
    Describe how the model works:Object detected when shown in camera field of view.
    Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:Not Applicable
    Technical Limitations:Model needs to be transferred learned before deployment.
    Verified to have met prescribed NVIDIA standards:Yes
    Performance Metrics:Accuracy
    Potential Known Risks:None Known
    Licensing:http://creativecommons.org/licenses/by/4.0/