I have seen other loss functions implemented, yours is more similar to that of Yolo V1, my question is:
1) Why not use categorical crosss entrophy in class predictions ?
2) In the IoU filter, maked in the computation of noobjs_loss you put that
higthst_iou = tf.math.reduce_max(iou, axis=-1)mask = (tf.cast(higthst_iou < 0.6, dtype=tf.float32)[..., None] * (1 - true_object)) # noobj mask
but, if we have to penalize higest IoU, why put < 0.6 and not > 0.6
I have seen other loss functions implemented, yours is more similar to that of Yolo V1, my question is:
1) Why not use categorical crosss entrophy in class predictions ? 2) In the IoU filter, maked in the computation of noobjs_loss you put that
higthst_iou = tf.math.reduce_max(iou, axis=-1)mask = (tf.cast(higthst_iou < 0.6, dtype=tf.float32)[..., None] * (1 - true_object)) # noobj maskbut, if we have to penalize higest IoU, why put < 0.6 and not > 0.6thanks a lot! :D