DetectNetV2 recognizes the individual objects in an image. This model is ready for commercial use.
Get TAO Object Detection pre-trained models for YOLOV4, YOLOV3, FasterRCNN, SSD, DSSD, and RetinaNet architectures from NGC model registry
Get TAO EfficientDet Object Detection pre-trained models for DetectNet_v2 architecture from NGC model registry
Get TAO classification pre-trained models from NGC model registry
Get TAO Instance segmentation pre-trained models for MaskRCNN architecture from NGC
Get TAO Semantic segmentation pre-trained models for UNet architecture from NGC
Get Purpose-built models from NGC model registry:
Architecture Type: Convolution Neural Network (CNN)
Network Architecture: DetectNet_v2
This model card contains pretrained weights that may be used as a starting point with the DetectNet_v2 object detection networks in Train Adapt Optimize (TAO) Toolkit to facilitate transfer learning.
Input Type(s): Image
Input Format(s): Red, Green, Blue (RGB)
Input Parameters: 3D
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
Output Type(s): Label(s), Bounding-Box(es), Confidence Scores
Output Format: Label: Text String(s); Bounding Box: (x-coordinate, y-coordinate, width, height), Confidence Scores: Floating Point
Other Properties Related to Output: Category Label(s): (Labels of object detected), Bounding Box Coordinates, Confidence Scores
Runtime Engine(s):
Supported Hardware Architecture(s):
Supported Operating System(s):
Note: These are unpruned models with just the feature extractor weights, and may not be used without re-training in an object detection application
Note: When using the ResNet34 model, please set the all_projections field in the model_config to False. For more information about this parameter, please refer to the TAO Getting Started Guide.
Note: The pre-trained weights in this model are only for DetectNet_v2 object detection networks and shouldn't be used for YOLOV3, RetinaNet, FasterRCNN, SSD and DSSD based object detection models. For pre-trained weights for those models, click here
Link: https://github.com/openimages/dataset/blob/main/READMEV3.md
Data Collection Method by dataset:
Labeling Method by dataset:
Properties:
Roughly 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.
Link: https://github.com/openimages/dataset/blob/main/READMEV3.md
Data Collection Method by dataset:
Labeling Method by dataset:
Properties: 15,000 test images from Google OpenImages Version Three (3) dataset.
The object detection apps in TAO expect data in KITTI file format. TAO provides a simple command line interface to train a deep learning model for object detection.
The models in this model area are only compatible with TAO Toolkit. For more information about the TAO container, please visit the TAO container page.
Install the NGC CLI from ngc.nvidia.com
Configure the NGC CLI using the following command
ngc config set
ngc registry model list nvidia/tao_pretrained_detectnet_v2:*
ngc registry model download-version nvidia/tao_pretrained_detectnet_v2:<template> --dest <path>
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
Configure the NGC command line interface using the command mentioned below and follow the prompts.
ngc config set
ngc registry resource download-version "nvidia/tao_cv_samples:v1.0.2"
jupyter notebook --ip 0.0.0.0 --port 8888 --allow-root
http://0.0.0.0:8888
If you wish to run view the notebook from a remote client, please modify the URL as follows:
http://a.b.c.d:8888
Where, the a.b.c.d is the IP address of the machine running the container.
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 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.