Training sample without object

[littlekittel]

I want to manipulate input images, so that the algo thinks there is no object in the image.
So I want to set:
gt_boxes = [[]]
classes = [[]]
after loading each training sample.
I am getting the following dimensions error which I can not solve.
Any suggestions?

`Traceback (most recent call last):
File "/home/markus/anaconda3/envs/dpatch/lib/python3.6/multiprocessing/pool.py", line 119, in worker
result = (True, func(*args, **kwds))
File "/home/markus/anaconda3/envs/dpatch/lib/python3.6/multiprocessing/pool.py", line 44, in mapstar
return list(map(*args))
File "/home/markus/DPatch-master/darknet.py", line 83, in _process_batch
np.ascontiguousarray(gt_boxes_b, dtype=np.float)
File "/utils/bbox.pyx", line 116, in cython_bbox.bbox_ious (bbox.c:2878)
File "/utils/bbox.pyx", line 140, in cython_bbox.bbox_ious_c (bbox.c:3114)
IndexError: Out of bounds on buffer access (axis 1)
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/home/markus/DPatch-master/train.py", line 100, in
bbox_pred, iou_pred, prob_pred = net(im_data, gt_boxes, gt_classes, dontcare, size_index, attack="targeted")
File "/home/markus/anaconda3/envs/dpatch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/markus/DPatch-master/darknet.py", line 269, in forward
size_index)
File "/home/markus/DPatch-master/darknet.py", line 306, in _build_target
for b in range(bsize)))
File "/home/markus/anaconda3/envs/dpatch/lib/python3.6/multiprocessing/pool.py", line 266, in map
return self._map_async(func, iterable, mapstar, chunksize).get()
File "/home/markus/anaconda3/envs/dpatch/lib/python3.6/multiprocessing/pool.py", line 644, in get
raise self._value
IndexError: Out of bounds on buffer access (axis 1)

Process finished with exit code 1`