Question about data augment for targets about second.pytorch

[traveller59]

sorry for late reply.

1. target collision is estimated in noise_per_object, if collision happens, current noise is dropped and try next noise until valid noise is found.
2. I haven't tried this because I don't think this can increase performance.

[godspeed1989]

Thanks!
For question 1, do you mean the function noise_per_object_v3_ in second.core.preprocess file?
I am afraid can't figure out your explanation from it.
Could you give me a little more tips?

[traveller59]

the function noise_per_object_v3_ first generate noises with shape [num_boxes, num_try, noise_ndim], then apply noise sequentially. For every box, this function firstly compute location after apply noise, then test collision between this box and other boxes, if collision exists, then drop this noise and try next one.

[godspeed1989]

Thank you very much.
The collision detection and selection are done in function noise_per_box_v2_

[godspeed1989]

Sorry to bother you again.

I notice in all .config files, global_random_rotation_range_per_object under database_sampler are all set to [0,0]
Which means _enable_global_rot are always False.

second.pytorch/second/core/sample_ops.py

Lines 80 to 88 in 93e5bb7

	self._enable_global_rot = False
	if global_rot_range is not None:
	if not isinstance(global_rot_range, (list, tuple, np.ndarray)):
	global_rot_range = [-global_rot_range, global_rot_range]
	else:
	assert shape_mergeable(global_rot_range, [2])
	if np.abs(global_rot_range[0] -
	global_rot_range[1]) >= 1e-3:
	self._enable_global_rot = True

and prep.noise_per_object_v3_ will never be called.

second.pytorch/second/core/sample_ops.py

Lines 249 to 258 in 93e5bb7

	if self._enable_global_rot:
	# place samples to any place in a circle.
	prep.noise_per_object_v3_(
	boxes,
	None,
	valid_mask,
	0,
	0,
	self._global_rot_range,
	num_try=100)

That's wired. Does this function really useful?

Thank you in advance.

[godspeed1989]

Sorry to bother you again.
But i still want to know the answer about my last question. :)