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
Pretrained ConvNeXtV2
Model
NVIDIA
NVIDIA
Pretrained ConvNeXtV2

Pretrained ConvNextv2 backbone models to facilitate transfer learning for commercially viable models.

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 Applications & Domains:Generating image embedding for image classification, segmentation, and detection tasks.
Model Type:Object Classification
Intended Users:This model is intended for developers building CV applications.
Output:Embedding
Describe how the model works:This model takes RGB images as input and outputs classifier embeddings.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of:Not Applicable
Technical Limitations:This model may experience challenges with detection and classification for non-Flicker style data, such as medical, satellite and industrial data.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Zero-shot KNN
Potential Known Risks:This model may inaccurately predict object class.
Licensing:NVIDIA Open Model License