Open Images Pre-trained DetectNet_v2¶
Object detection is a popular computer vision technique that can detect one or multiple objects in a frame. Object detection will recognize the individual objects in an image and place bounding boxes around the object. This model object contains pretrained weights that may be used to initialize the DetectNet_v2 object detection networks in TAO Toolkit to facilitate transfer learning.
It is trained on a subset of the Google OpenImages dataset.
The following backbones are supported with DetectNet_v2 networks:
These are unpruned models with just the feature extractor weights, and may not be used without re-training in an object detection application
When using the ResNet34 model, please set the
all_projectionsfield in the
False. For more information about this parameter, please refer to the model config section in the detectnet_v2 documentation.
The pre-trained weights in this model are only for DetectNet_v2 object detection networks and shouldn’t be used for YOLOv3/YOLOv4/YOLOv4-tiny, RetinaNet, FasterRCNN, SSD and DSSD based object detection models.
You may find more information about these models on NGC.