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
PeopleNet
Model
NVIDIA
NVIDIA
PeopleNet

3 class object detection network to detect people in an image.

22 Versions
pruned_quantized_decrypted_v2.3.4Signed
09/20/2024 7:36 AM UTC8.4 MB
deployable_quantized_onnx_v2.6.3
09/20/2024 7:35 AM UTC84.83 MB
deployable_quantized_onnx_v2.6.2Selected
04/11/2024 10:30 PM UTC84.83 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
pruned_quantized_decrypted_v2.3.3
08/18/2023 6:41 PM UTC8.4 MB
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureDetectNet_v2
7. RUNTIME(S)Deepstream
8. Supported OSLINUX, LINUX4TEGRA
6. TrainableFalse
5. OutputTYPE: LABEL, BOUNDING BOX; LABEL CLASSES: PERSON, BAG, FACE; DIMENSION: 2D; RESOLUTION: LABELS-1X3, BBOX-1X4
3. Model ArchitectureResNet-34
1. DescriptionDetects people in 2D RGB image. Can detect bags and faces too.
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
9. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
trainable_unencrypted_v2.6
08/14/2023 5:40 PM UTC85.29 MB
pruned_quantized_v2.3.2
12/09/2022 8:08 PM UTC8.54 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
deployable_quantized_v2.6.1
12/09/2022 8:08 PM UTC85.03 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
deployable_quantized_v2.5.2
12/09/2022 8:08 PM UTC85.03 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
deployable_quantized_v2.6
05/25/2022 9:52 PM UTC85.03 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureDetectNet_v2
6. RUNTIME(S)Deepstream
8. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
5. OutputTYPE: LABEL, BOUNDING BOX; LABEL CLASSES: PERSON, BAG, FACE; DIMENSION: 2D; RESOLUTION: LABELS-1X3, BBOX-1X4
3. Model ArchitectureResNet-34
7. Supported OSLINUX, LINUX4TEGRA
1. DescriptionDetects people in 2D RGB image. Can detect bags and faces too.
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
trainable_v2.6
05/25/2022 9:52 PM UTC85.51 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureDetectNet_v2
6. RUNTIME(S)Deepstream
8. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
5. OutputTYPE: LABEL, BOUNDING BOX; LABEL CLASSES: PERSON, BAG, FACE; DIMENSION: 2D; RESOLUTION: LABELS-1X3, BBOX-1X4
3. Model ArchitectureResNet-34
7. Supported OSLINUX, LINUX4TEGRA
1. DescriptionDetects people in 2D RGB image. Can detect bags and faces too.
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3