TypeError: tuple indices must be integers or slices, not tuple

[adityamukherjee42]

i have been facing this issue not able to know which line please help
TypeError Traceback (most recent call last)
in
26 if detections is not None:
27 detections=np.array(detections)
---> 28 tracked_objects = mot_tracker.update(detections)
29 detections=torch.from_numpy(detections)
30 unique_labels = detections[:, -1].cpu().unique()

E:\Football player tracking\sort.py in update(self, dets)
207
208 #update matched trackers with assigned detections
--> 209 for t,trk in enumerate(self.trackers):
210 if(t not in unmatched_trks):
211 d = matched[np.where(matched[:,1]==t)[0],0]

E:\Football player tracking\sort.py in associate_detections_to_trackers(detections, trackers, iou_threshold)
150 for d,det in enumerate(detections):
151 if(d not in matched_indices[:,0]):
--> 152 unmatched_detections.append(d)
153 unmatched_trackers = []
154 for t,trk in enumerate(trackers):

TypeError: tuple indices must be integers or slices, not tuple

[InputBlackBoxOutput]

I am facing a similar issue. I speculate that the code is broken because of sklearn.utils.linear_assignment_ which has to be changed to scipy.optimize.linear_sum_assignment

Code

        detections = [[start_point[0], start_point[1], end_point[0], end_point[1], confidence] for (start_point, end_point, label, confidence) in results]
        # np.set_printoptions(formatter={'float': lambda x: "{0:0.3f}".format(100)})
        dets = np.asarray(detections)
        print(dets)
        tracks = tracker.update(dets)

Debug output with error:

[]
[]
[]
[]
[]
[]
[]
[[109.         147.         170.         173.           0.50095928]]
[[105.         141.         171.         171.           0.36380956]]
Traceback (most recent call last):
  File "C:\Users\admin\Desktop\commits\virtual_line\run.py", line 100, in <module>
    tracks = tracker.update(dets)
  File "C:\Users\admin\Desktop\commits\virtual_line\sort.py", line 203, in update
    matched, unmatched_dets, unmatched_trks = associate_detections_to_trackers(dets,trks)
  File "C:\Users\admin\Desktop\commits\virtual_line\sort.py", line 144, in associate_detections_to_trackers
    if(d not in matched_indices[:,0]):
TypeError: tuple indices must be integers or slices, not tuple

@adityamukherjee42 Were you able to solve the issue?

[adityamukherjee42]

No man still trying to

[InputBlackBoxOutput]

@adityamukherjee42 Found a solution
Use pip to install lap
Comment out the import and use the following function.

def linear_assignment(cost_matrix):
  try:
    import lap
    _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
    return np.array([[y[i], i] for i in x if i >= 0])
  except ImportError:
    from scipy.optimize import linear_sum_assignment
    x, y = linear_sum_assignment(cost_matrix)
    return np.array(list(zip(x, y)))

I hope this helps

[cocoph]

@adityamukherjee42 Found a solution
Use pip to install lap
Comment out the import and use the following function.

def linear_assignment(cost_matrix):
  try:
    import lap
    _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
    return np.array([[y[i], i] for i in x if i >= 0])
  except ImportError:
    from scipy.optimize import linear_sum_assignment
    x, y = linear_sum_assignment(cost_matrix)
    return np.array(list(zip(x, y)))

I hope this helps

I'm facing the same issue, can you please explain more where to put those functions?

[InputBlackBoxOutput]

sklearn.utils.linear_assignment_ was replaced with scipy.optimize.linear_sum_assignment since the latter was pruned in the current version. I found the above function in a previous commit.

Follows these steps to fix the bug.

1. Comment out the import

# from scipy.optimize import linear_sum_assignment as linear_assignment

2. Use pip to install lap

3. Copy and paste the above function in the sort.py file

[cocoph]

sklearn.utils.linear_assignment_ was replaced with scipy.optimize.linear_sum_assignment since the latter was pruned in the current version. I found the above function in a previous commit.

Follows these steps to fix the bug.

1. Comment out the import

# from scipy.optimize import linear_sum_assignment as linear_assignment

1. Use pip to install lap
2. Copy and paste the above function in the sort.py file

It's working now, many thanks

[vkavin4201]

Facing a ValueError now
33 try:
34 import lap
---> 35 _, x, y = lap.lapjv(cost_matrix, extend_cost=True)
36 return np.array([[y[i], i] for i in x if i >= 0])
37 except ImportError:

lap/_lapjv.pyx in lap._lapjv.lapjv()

/usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py in _amax(a, axis, out, keepdims, initial, where)
38 def _amax(a, axis=None, out=None, keepdims=False,
39 initial=_NoValue, where=True):
---> 40 return umr_maximum(a, axis, None, out, keepdims, initial, where)
41
42 def _amin(a, axis=None, out=None, keepdims=False,

ValueError: zero-size array to reduction operation maximum which has no identity