ContainersNVIDIADeepSeek-R1NVIDIALlama-3.1-Nemotron-70B-InstructNVIDIAPyTorch
CollectionsNVIDIAOmniverse Kit (FB)NVIDIADeepStream SDKNVIDIAOmniverse Kit App Streaming
ModelsNVIDIAStyleGAN3 pretrained modelsNVIDIAPeopleNetNVIDIATrafficCamNet
ResourcesNVIDIAKit SDK - Windows (PB25h1)NVIDIAKit SDK - Linux (PB25h1)NVIDIARiva Skills Quick Start
Helm ChartsNVIDIAGPU OperatorNVIDIANVIDIA NIM Operator
NVIDIA
NVIDIA
Mask2Former
Model
NVIDIA
NVIDIA
Mask2Former

Binary instance segmentation model trained on COCO data.

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:Segmenting (Semantic, Instance, Panoptic)
Model Type:Object Segmentation
Intended Users:This model is intended for developers building object segmentation applications.
Output:Segmentation Masks, Category Labels
Describe how the model works:This model predicts masks and the associated labels.
Technical Limitations:The model may have difficulties in non-Flickr style data like medical, satellite, and industrial data.
Verified to have met prescribed NVIDIA standards:Yes
Performance Metrics:Mean Intersection over Union (mIoU)
Licensing:NVIDIA Open Model License