[{"_1":2,"_3":-5,"_4":-5},"loaderData",{"_5":6,"_7":8,"_9":10,"_11":12},"actionData","errors","root",{"_250":251,"_252":253,"_254":255,"_256":257,"_258":259,"_260":20,"_261":262,"_263":264,"_265":20,"_266":20,"_267":20,"_268":20,"_269":270,"_271":-5,"_272":273,"_274":275,"_276":277,"_278":279,"_280":281,"_282":283,"_284":-5,"_285":20,"_286":-5,"_287":288,"_289":290,"_77":291,"_292":293,"_294":295,"_296":297,"_298":299,"_300":20,"_15":16,"_17":301,"_19":20,"_21":302,"_23":303,"_25":304},"routes/orgs/$orgName/$teamName/$resourceType/$resourceId/$version/route",{"_63":64,"_13":65,"_66":67,"_68":69,"_70":20,"_71":72,"_73":20,"_74":20,"_75":76,"_77":78,"_79":-5,"_80":81,"_82":-5,"_83":84,"_85":86,"_87":88,"_89":90,"_15":16,"_17":91,"_19":20,"_21":92,"_23":93,"_25":94},"routes/orgs/$orgName/$teamName/$resourceType/$resourceId/$version/model-card/route",{"_15":16,"_17":57,"_19":20,"_21":58,"_23":59,"_25":60},"routes/orgs/$orgName/$teamName/$resourceType/$resourceId/$version/model-card/bias/route",{"_13":14,"_15":16,"_17":18,"_19":20,"_21":22,"_23":24,"_25":26},"html","\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n

tr:nth-child(odd)]:bg-surface-sunken\">

Field	Response
Participation considerations from adversely impacted groups (protected classes) in model design and testing:	None of the Above
Measures taken to mitigate against unwanted bias:	No measures taken to mitigate against unwanted bias.

","traceId","c0aab24cd18c4810baea53571dba0eed","traceStartTime",1789132391002,"isStaleResponse",false,"notifications",[],"toasts",[],"apiCalls",[27,28,29,30,31,32],{"_33":47,"_35":55,"_37":52,"_39":53,"_41":56,"_43":44},{"_33":47,"_35":51,"_37":52,"_39":53,"_41":54,"_43":44},{"_33":47,"_35":50,"_37":49,"_39":-5,"_41":-5,"_43":44},{"_33":47,"_35":48,"_37":49,"_39":-5,"_41":-5,"_43":44},{"_33":45,"_35":46,"_37":38,"_39":40,"_41":42,"_43":44},{"_33":34,"_35":36,"_37":38,"_39":40,"_41":42,"_43":44},"apiTag","subscription-api","path","/v2/users/me/subscriptions","status","error","httpStatus",401,"durationMs",3,"retryCount",0,"oms-api","/v2/users/me","models-api","/v2/models/org/nvidia/team/tao/pretrained_instance_segmentation/collections?page-number=0&page-size=1","pending","/v2/models/nvidia/tao/pretrained_instance_segmentation/versions/resnet10","/v2/models/nvidia/tao/pretrained_instance_segmentation/versions?page-size=100&page-number=0&sort-order=CREATED_DATE_DESC","success",200,53,"/v2/models/nvidia/tao/pretrained_instance_segmentation?resolve-labels=true&remove-unresolved-labels=true",67,1789132390920,[],[],[61,62],{"_33":45,"_35":46,"_37":49,"_39":-5,"_41":-5,"_43":44},{"_33":34,"_35":36,"_37":49,"_39":-5,"_41":-5,"_43":44},"resource",{"_143":155,"_156":157,"_158":159,"_160":161,"_103":104,"_105":106,"_162":163,"_110":164,"_165":166,"_116":167,"_168":169,"_170":109,"_171":-7,"_172":-7,"_173":174,"_175":176,"_177":88,"_178":119,"_179":-5,"_180":-7,"_181":-7,"_182":183,"_184":185,"_186":187,"_188":189,"_190":191,"_192":193,"_194":195,"_196":197,"_198":199,"_200":20},"

TAO Pretrained Instance Segmentation

Description:

The Instance Segmentation model identifies each instance of multiple objects in a frame at the pixel level. This model is ready for commercial use.

References:

Other TAO Pre-trained Models

\n
Get TAO Object Detection pre-trained models for YOLOV4, YOLOV3, FasterRCNN, SSD, DSSD, and RetinaNet architectures from NGC model registry
\n
\n
Get TAO DetectNet_v2 Object Detection pre-trained models for DetectNet_v2 architecture from NGC model registry
\n
\n
Get TAO EfficientDet Object Detection pre-trained models for DetectNet_v2 architecture from NGC model registry
\n
\n
Get TAO classification pre-trained models from NGC model registry
\n
\n
Get TAO Semantic segmentation pre-trained models for UNet architecture from NGC
\n
\n
Get Purpose-built models from NGC model registry:
\n
- PeopleNet
- TrafficCamNet
- DashCamNet
- FaceDetectIR
- VehicleMakeNet
- VehicleTypeNet
- PeopleSegNet
- PeopleSemSegNet
- License Plate Detection
- License Plate Recognition
- Facial Landmark
- FaceDetect
- 2D Body Pose Net
- ActionRecognitionNet
\n

Model Architecture:

Architecture Type: MaskRCNN
\nNetwork Architecture: ResNet

Input:

Input Type(s): Image
\nInput Format(s): Red, Green, Blue (RGB)
\nInput Parameters: 3D
\nOther Properties Related to Input: Minimum Resolution: B X 3 X 224 X 224; Maximum Resolution: B X 3 X 518 X 518; No minimum bit depth, alpha, or gamma

Output:

Output Type(s): Label(s), Bounding-Box(es), Segmentation Mask
\nOutput Format: Label: Text String(s); Bounding Box: (x-coordinate, y-coordinate, width, height), Segmentation Mask: 2D
\nOther Properties Related to Output: Category Label(s): Object(s) detected, Confidence Scores, Segmentation Mask

Software Integration:

Runtime Engine(s):

TAO - 5.2
DeepStream - 6.1

Supported Hardware Architecture(s):

Ampere
Jetson
Hopper
Lovelace
Pascal
Turing
Volta

Supported Operating System(s):

Linux
Linux 4 Tegra

Model Version(s):

resnet10
resnet18
resnet34
resnet50
resnet101

Training & Evaluation:

Training Dataset:

Link: https://github.com/openimages/dataset/blob/main/READMEV3.md

Data Collection Method by dataset:

Unknown

Labeling Method by dataset:

Unknown

Properties:
\nRoughly 400,000 images and 7,000 validation images across thousands of classes as defined by Google OpenImages Version Three (3) dataset. Most of the human verifications have been done with in-house annotators at Google. A smaller part has been done with crowd-sourced verification from Image Labeler: Crowdsource app, g.co/imagelabeler.

Evaluation Dataset:

Link: https://github.com/openimages/dataset/blob/main/READMEV3.md

Data Collection Method by dataset:

Unknown

Labeling Method by dataset:

Unknown

Properties:
\n15,000 test images from Google OpenImages Version Three (3) dataset.

Instance Segmentation Using TAO

Instance segmentation is a popular computer vision technique that can identify each instance of multiple objects in a frame at the pixel level. Instance segmentation will not only produce bounding boxes around the object, but also segmentation masks. This model card contains pretrained weights that may be used as a starting point with the following instance segmentation networks in Train Adapt Optimize (TAO) Toolkit to facilitate transfer learning.

Following instance segmentation architecture are supported:

MaskRCNN

The pre-trained weights are trained on a subset of the Google OpenImages dataset. Following backbones are supported with these MaskRCNN networks.

resnet10/resnet18/resnet34/resnet50/resnet101

To see the full list of all the backbones, scroll over to the version history tab.

Note: These are unpruned models with just the feature extractor weights, and may not be used without re-training in an Instance segmentation application

Training Instance Segmentation Models Using TAO

The instance segmentation apps in TAO expect data in COCO format. TAO provides a simple command line interface to train a deep learning model for instance segmentation.

The models in this model area are only compatible with TAO Toolkit. For more information about using this model with TAO, please view the instructions here to install the TAO Launcher CLI and use with the instance segmentation trainer in TAO.

\n
Install the NGC CLI from ngc.nvidia.com
\n
\n
Configure the NGC CLI using the following command
\n

ngc config set\n

\n
To view all the backbones that are supported by Instance segmentation architecture in TAO:
\n
```
ngc registry model list nvidia/tao/pretrained_instance_segmentation:*\n
```
\n

Download the model:

--dest \n\">

ngc registry model download-version nvidia/tao/pretrained_instance_segmentation:<template> --dest <path>\n

Instructions to run the sample notebook

\n
Get the NGC API key from the SETUP tab on the left. Please store this key for future use. Detailed instructions can be found here
\n
\n
Configure the NGC command line interface using the command mentioned below and follow the prompts.
\n

ngc config set\n

Download the sample notebooks from NGC using the command below

ngc registry resource download-version \"nvidia/tao_cv_samples:v1.0.2\"\n

Invoke the jupyter notebook using the following command

jupyter notebook --ip 0.0.0.0 --port 8888 --allow-root\n

\n
Open an internet browser and type in the following URL to start running the notebooks when running on a local machine.
\n
```
http://0.0.0.0:8888\n
```
\n
If you wish to run view the notebook from a remote client, please modify the URL as follows:
\n
```
http://a.b.c.d:8888\n
```
\n
Where, the a.b.c.d is the IP address of the machine running the container.
\n

Technical blogs

Access the latest in Vision AI development workflows with NVIDIA TAO Toolkit 5.0.
Improve accuracy and robustness of vision ai models with vision transformers and NVIDIA TAO.
Train like a ‘pro’ without being an AI expert using TAO AutoML.
Create Custom AI models using NVIDIA TAO Toolkit with Azure Machine Learning .
Developing and Deploying AI-powered Robots with NVIDIA Isaac Sim and NVIDIA TAO
Learn endless ways to adapt and supercharge your AI workflows with TAO - Whitepaper.
Customize Action Recognition with TAO and deploy with DeepStream.
Read the 2 part blog on training and optimizing 2D body pose estimation model with TAO - Part 1 | Part 2
Learn how to train real-time License plate detection and recognition app with TAO and DeepStream.
Model accuracy is extremely important; learn how you can achieve state of the art accuracy for classification and object detection models using TAO.

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Promise and the Explainability, Bias, Safety & Security, and Privacy Subcards.

","resourceVersions",[137,138,139,140,141,142],"resourceVersionsTotal",5,"hasMoreVersions","versionMetadata",{"_108":109,"_110":111,"_37":112,"_113":-5,"_114":115,"_116":117,"_118":119,"_120":121,"_122":20,"_123":-5,"_124":20,"_125":-5,"_126":20,"_127":-5,"_128":20,"_129":-5,"_130":20,"_131":-5,"_132":20,"_133":-5,"_134":20,"_135":136},"versionNotFound","isLoggedIn","latestVersionPath","/orgs/nvidia/tao/models/pretrained_instance_segmentation/-","version","-","imageReference","cliDownloadCommand","ngc registry model download-version nvidia/tao/pretrained_instance_segmentation:resnet10","helmFetchCommand","viewAllVersionsPath","/orgs/nvidia/tao/models/pretrained_instance_segmentation/-/version-history","accessCheckResult",{"_107":88},"hasRelatedCollections",true,"context",{"_103":104,"_105":106},1789132391052,[],[],[95,96,97,98,99,100],{"_33":47,"_35":55,"_37":52,"_39":53,"_41":56,"_43":44},{"_33":47,"_35":51,"_37":52,"_39":53,"_41":54,"_43":44},{"_33":47,"_35":50,"_37":52,"_39":53,"_41":102,"_43":44},{"_33":47,"_35":48,"_37":52,"_39":53,"_41":101,"_43":44},{"_33":45,"_35":46,"_37":38,"_39":40,"_41":42,"_43":44},{"_33":34,"_35":36,"_37":38,"_39":40,"_41":42,"_43":44},85,48,"orgName","nvidia","teamName","tao","allowed","versionId","resnet10","description","","UPLOAD_COMPLETE","releaseType","createdDate",["D",1629317518597],"updatedDate",["D",1740841154090],"totalSizeInBytes",40175904,"totalFileCount",1,"isSigned","malwareScanStatus","isScanned","releaseNotes","hasReleaseNotes","setup","hasSetup","quickStartGuide","hasQuickStartGuide","advanced","hasAdvanced","performance","hasPerformance","policies",[],{"_143":78,"_144":154,"_113":-5,"_122":20,"_124":20,"_135":145,"_126":20},{"_143":152,"_144":152,"_113":-5,"_122":20,"_124":20,"_135":153,"_126":20},{"_143":150,"_144":150,"_113":-5,"_122":20,"_124":20,"_135":151,"_126":20},{"_143":148,"_144":148,"_113":-5,"_122":20,"_124":20,"_135":149,"_126":20},{"_143":146,"_144":146,"_113":-5,"_122":20,"_124":20,"_135":147,"_126":20},{"_143":109,"_144":109,"_113":-5,"_122":20,"_124":20,"_135":145,"_126":20},"id","name",[],"resnet18",[],"resnet34",[],"resnet50",[],"resnet101",[],"Latest (resnet10)","nvidia/tao/pretrained_instance_segmentation","key","nvidia/tao/models/pretrained_instance_segmentation","resourceType","models","resourceId","pretrained_instance_segmentation","shortDescription","Pretrained weights to facilitate transfer learning using TAO Toolkit.","# TAO Pretrained Instance Segmentation\n\n## Description:\nThe Instance Segmentation model identifies each instance of multiple objects in a frame at the pixel level. This model is ready for commercial use. \n\n## References:\n### Other TAO Pre-trained Models \n- Get [TAO Object Detection](https://ngc.nvidia.com/catalog/models/nvidia:tao:pretrained_object_detection) pre-trained models for **YOLOV4, YOLOV3, FasterRCNN, SSD, DSSD, and RetinaNet** architectures from NGC model registry\n- Get [TAO DetectNet_v2 Object Detection](https://ngc.nvidia.com/catalog/models/nvidia:tao:pretrained_detectnet_v2) pre-trained models for **DetectNet_v2** architecture from NGC model registry\n- Get [TAO EfficientDet Object Detection](https://ngc.nvidia.com/catalog/models/nvidia:tao:pretrained_efficientdet) pre-trained models for **DetectNet_v2** architecture from NGC model registry\n- Get [TAO classification](https://ngc.nvidia.com/catalog/models/nvidia:tao:pretrained_classification) pre-trained models from NGC model registry\n- Get [TAO Semantic segmentation](https://ngc.nvidia.com/catalog/models/nvidia:tao:pretrained_semantic_segmentation) pre-trained models for **UNet** architecture from NGC\n\n- Get Purpose-built models from NGC model registry:\n - [PeopleNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:peoplenet)\n - [TrafficCamNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:trafficcamnet)\n - [DashCamNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:dashcamnet)\n - [FaceDetectIR](https://ngc.nvidia.com/catalog/models/nvidia:tao:facedetectir)\n - [VehicleMakeNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:vehiclemakenet)\n - [VehicleTypeNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:vehicletypenet)\n - [PeopleSegNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:peoplesegnet)\n - [PeopleSemSegNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:peoplesemsegnet)\n - [License Plate Detection](https://ngc.nvidia.com/catalog/models/nvidia:tao:lpdnet)\n - [License Plate Recognition](https://ngc.nvidia.com/catalog/models/nvidia:tao:lprnet)\n - [Facial Landmark](https://ngc.nvidia.com/catalog/models/nvidia:tao:fpenet)\n - [FaceDetect](https://ngc.nvidia.com/catalog/models/nvidia:facenet)\n - [2D Body Pose Net](https://ngc.nvidia.com/catalog/models/nvidia:tao:bodyposenet)\n - [ActionRecognitionNet](https://ngc.nvidia.com/catalog/models/nvidia:tao:actionrecognitionnet)\n\n## Model Architecture: \n**Architecture Type:** MaskRCNN
\n**Network Architecture:** ResNet
\n\n\n## Input:\n**Input Type(s):** Image
\n**Input Format(s):** Red, Green, Blue (RGB)
\n**Input Parameters:** 3D
\n**Other Properties Related to Input:** Minimum Resolution: B X 3 X 224 X 224; Maximum Resolution: B X 3 X 518 X 518; No minimum bit depth, alpha, or gamma
\n\n## Output:\n**Output Type(s):** Label(s), Bounding-Box(es), Segmentation Mask
\n**Output Format:** Label: Text String(s); Bounding Box: (x-coordinate, y-coordinate, width, height), Segmentation Mask: 2D
\n**Other Properties Related to Output:** Category Label(s): Object(s) detected, Confidence Scores, Segmentation Mask
\n\n## Software Integration:\n**Runtime Engine(s):** \n* TAO - 5.2
\n* DeepStream - 6.1
\n\n**Supported Hardware Architecture(s):**
\n* Ampere
\n* Jetson
\n* Hopper
\n* Lovelace
\n* Pascal
\n* Turing
\n* Volta
\n\n**Supported Operating System(s):**
\n* Linux
\n* Linux 4 Tegra
\n\n## Model Version(s): \n- resnet10\n- resnet18\n- resnet34\n- resnet50\n- resnet101\n\n\n## Training & Evaluation: \n\n## Training Dataset:\n**Link:** https://github.com/openimages/dataset/blob/main/READMEV3.md
\n\n**Data Collection Method by dataset:**
\n* Unknown
\n\n**Labeling Method by dataset:**
\n* Unknown
\n\n**Properties:**
\nRoughly 400,000 images and 7,000 validation images across thousands of classes as defined by [Google OpenImages Version Three (3) dataset](https://github.com/openimages/dataset/blob/main/READMEV3.md). Most of the human verifications have been done with in-house annotators at Google. A smaller part has been done with crowd-sourced verification from Image Labeler: [Crowdsource app](http://play.google.com/store/apps/details?id=com.google.android.apps.village.boond), [g.co/imagelabeler](http://g.co/imagelabeler).\n\n\n## Evaluation Dataset:\n**Link:** https://github.com/openimages/dataset/blob/main/READMEV3.md
\n\n**Data Collection Method by dataset:**
\n* Unknown
\n\n**Labeling Method by dataset:**
\n* Unknown
\n\n**Properties:**
\n15,000 test images from [Google OpenImages Version Three (3) dataset](https://github.com/openimages/dataset/blob/main/READMEV3.md).\n\n## Instance Segmentation Using TAO \n\nInstance segmentation is a popular computer vision technique that can identify each instance of multiple objects in a frame at the pixel level. Instance segmentation will not only produce bounding boxes around the object, but also segmentation masks. This model card contains pretrained weights that may be used as a starting point with the following instance segmentation networks in Train Adapt Optimize (TAO) Toolkit to facilitate transfer learning.\n\nFollowing instance segmentation architecture are supported:\n\n- MaskRCNN\n\nThe pre-trained weights are trained on a subset of the Google OpenImages dataset. Following backbones are supported with these MaskRCNN networks.\n\n- resnet10/resnet18/resnet34/resnet50/resnet101\n\nTo see the full list of all the backbones, scroll over to the version history tab.\n\n***Note:*** These are unpruned models with just the feature extractor weights, and may not be used without re-training in an Instance segmentation application\n\n## Training Instance Segmentation Models Using TAO \n\nThe instance segmentation apps in TAO expect data in COCO format. TAO provides a simple command line interface to train a deep learning model for instance segmentation.\n\nThe models in this model area are only compatible with TAO Toolkit. For more information about using this model with TAO, please view the instructions [here](https://docs.nvidia.com/tao/tao-toolkit/text/tao_launcher.html) to install the TAO Launcher CLI and use with the [instance segmentation](https://docs.nvidia.com/tao/tao-toolkit/text/instance_segmentation/index.html) trainer in TAO.\n\n1. Install the NGC CLI from `ngc.nvidia.com`\n\n2. Configure the NGC CLI using the following command\n\n ```sh\n ngc config set\n ```\n\n3. To view all the backbones that are supported by Instance segmentation architecture in TAO:\n\n ```sh\n ngc registry model list nvidia/tao/pretrained_instance_segmentation:*\n ```\n\n4. Download the model:\n\n ```sh\n ngc registry model download-version nvidia/tao/pretrained_instance_segmentation: