learn_aug_for_object_detection.numpy
learn_aug_for_object_detection.numpy copied to clipboard
bug of _apply_multi_bbox_augmentation func
when i use _apply_multi_bbox_augmentation function with func_changes_bbox=false, this function shuffle the bbox order. but label order is not shuffle. I think, this can make problem of mislabeling.
np.random.shuffle(bboxes) change the order of bboxes. so below code should be changed with np.random.permutation()
if not func_changes_bbox: np.random.shuffle(bboxes) loop_bboxes = bboxes -> if not func_changes_bbox: loop_bboxes = np.random.permutation(bboxes)
np.random.shuffle(bboxes) change the order of bboxes. so below code should be changed with np.random.permutation()
if not func_changes_bbox: np.random.shuffle(bboxes) loop_bboxes = bboxes -> if not func_changes_bbox: loop_bboxes = np.random.permutation(bboxes)
i think this is the key reason why this code can not reproduce tensorflow result and i will fix and try
@Haijunlv Hi, any update here?