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
—
TAO Pretrained Classification
Model
—
TAO Pretrained Classification

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 image classification (weights are dataset dependent)
Model Type:Image Classification
Intended Users:This model is intended for developers building image classification pipelines.
Output:Category Label(s), Confidence Score(s)
Describe how the model works:Classifies images through popular model architectures.
Technical Limitations:This model may not perform well with more diverse object classes. Fine tining for the target domain is recommended.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Accuracy, Precision, Recall
Potential Known Risks:This model may fail to classify an object.
Licensing:https://creativecommons.org/licenses/by/4.0/