NVIDIA
NVIDIA
PeopleSemSegnet
Model
NVIDIA
NVIDIA
PeopleSemSegnet

Semantic segmentation of persons in an image.

15 Versions
deployable_shuffleseg_unet_onnx_v1.0.1Signed
09/20/2024 7:58 AM UTC3.73 MB
09/20/2024 7:57 AM UTC118.68 MB
09/20/2024 7:56 AM UTC118.72 MB
03/13/2024 10:48 PM UTC118.71 MBBatch Size: 1GPU: V100
03/13/2024 10:48 PM UTC3.73 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
03/13/2024 10:47 PM UTC118.71 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
08/22/2022 6:55 PM UTC118.71 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureUNet
7. RUNTIME(S)Deepstream
8. Supported OSLINUX, LINUX4TEGRA
6. TrainableFalse
5. OutputCategory label (person or background) for every pixel in the input image
1. DescriptionSemantic segmentation of persons in an image.
3. BackboneVanilla UNet Dynamic
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
9. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
08/22/2022 6:54 PM UTC118.71 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureUNet
7. RUNTIME(S)Deepstream
8. Supported OSLINUX, LINUX4TEGRA
6. TrainableFalse
5. OutputCategory label (person or background) for every pixel in the input image
1. DescriptionSemantic segmentation of persons in an image.
3. BackboneVanilla UNet Dynamic
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
9. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
05/25/2022 3:47 PM UTC118.71 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureUNet
6. RUNTIME(S)Deepstream
8. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
5. OutputCategory label (person or background) for every pixel in the input image
7. Supported OSLINUX, LINUX4TEGRA
1. DescriptionSemantic segmentation of persons in an image.
3. BackboneVanilla UNet Dynamic
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3
05/25/2022 3:44 PM UTC1.77 GBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
1. MODEL OVERVIEW
KeyValue
2. Model ArchitectureUNet
6. RUNTIME(S)Deepstream
8. Supported HardwareAll NVIDIA GPUS INCLUDING JETSON DEVICES
5. OutputCategory label (person or background) for every pixel in the input image
7. Supported OSLINUX, LINUX4TEGRA
1. DescriptionSemantic segmentation of persons in an image.
3. BackboneVanilla UNet Dynamic
4. InputTYPE: RGB IMAGE; DIMENSION: 2D; RESOLUTION: 1920X1080 RESIZED TO 960X544X3

NVIDIA uses cookies to improve your experience on our web site. We and our third-party partners also use cookies and other tools to collect and record information you provide as well as information about your interactions with our websites for performance improvement, analytics, and to assist in marketing efforts. By clicking "Accept All", you consent to our use of cookies and other tools as described in our Cookie Policy. You can manage your cookie settings by clicking on "Manage Settings." By continuing to use this site or by clicking one of the buttons below, you agree to our Terms of Service (which contains important waivers). Please see our Privacy Policy for more information on our privacy practices.