Equivalent of min_negatives_per_image

Please provide the following information when requesting support.

• Hardware (Xavier/Nano)
• Network Type (Yolo_v4 / object detection)
• TLT Version ( tao-toolkit-3-0-21-11)

In pipeline.cfg files when training in tensorflow it is possible to say how many negative examples to use in an image via min_negative_per_image. Is there a similar parameter available in TAO for YOLO specs?

Could you share a link for it? Thanks.

This from: https://github.com/tensorflow/models/blob/master/research/object_detection/samples/configs/ssd_mobilenet_v1_pets.config

Line 117

       hard_example_miner {
        num_hard_examples: 3000
        iou_threshold: 0.99
        loss_type: CLASSIFICATION
        max_negatives_per_positive: 3
        min_negatives_per_image: 3

You shared a link for SSD. So may I confirm that are you checking if there is a similar parameter available in TAO for SSD specs?

Thanks for getting back to me. Yes that is for SSD (I don’t think TF1.x has a yolo example), and yes are there similar parameters in TAO either for SSD and/or YOLO?

Many thanks

Thanks for the info. TAO does not have similar parameters.

Thanks for the clarification

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.