PeopleSegNet
Model
PeopleSegNet

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

7 Versions
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
10/26/2021 4:03 PM UTC70.54 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
08/25/2021 10:49 PM UTC345.12 MBAccuracy: 86120 Epochs
08/24/2021 10:54 PM UTC168.06 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
08/24/2021 10:54 PM UTC168.06 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100
08/24/2021 10:53 PM UTC344.68 MBAccuracy: 86120 EpochsBatch Size: 1GPU: V100
08/24/2021 10:53 PM UTC345.12 MBAccuracy: 80120 EpochsBatch Size: 1GPU: V100

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.