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
—
PeopleSegNet
Model
—
PeopleSegNet

1 class instance segmentation network to detect and segment instances of people in an image.

NVIDIA AI Enterprise Supported
7 Versions
deployable_v2.0.2
08/22/2022 6:55 PM UTC70.54 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureMaskRCNN
7. RUNTIME(S)Deepstream
8. Supported OSLINUX, LINUX4TEGRA
6. TrainableFalse
5. OutputCategory label (person), bounding-box coordinates and segmentation mask for each detected person in the input image.
1. DescriptionSegmentation of person instances in an image.
3. BackboneResNet-50
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
9. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
deployable_v2.0.1
10/26/2021 4:03 PM UTC70.54 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
trainable_v2.1
08/25/2021 10:49 PM UTC345.12 MBAccuracy: 86120 Epochs
deployable_v1.0
08/24/2021 10:54 PM UTC168.06 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
deployable_v2.0
08/24/2021 10:54 PM UTC168.06 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
trainable_v1.0Selected
08/24/2021 10:53 PM UTC344.68 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
trainable_v2.0
08/24/2021 10:53 PM UTC345.12 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100