Metric issues

[hust-kevin]

Hello
when I read 'metric.py'，I have a question

def update(self, labels, preds):
    # output: cls_prob_output, bbox_pred_output, cls_keep_inds, bbox_keep_inds
    # label: label, bbox_target

what do 'cls_keep_inds, bbox_keep_inds' mean ?
Looking forward to your reply

[Seanlinx]

@hust-kevin
They are the indices of valid training examples in a batch.
cls_keep_inds: hard examples of positives and negatives
bbox_keep_inds: positives and part faces