ValueError: shape mismatch: value array of shape (45,20) could not be broadcast to indexing result of shape (45,3)

[JunSun666]

Traceback (most recent call last):
File "C:/Users/Administrator/Desktop/ssd_kerass-master/SSD_training01.py", line 270, in
nb_worker=1)
File "D:\anaconda\envs\tensorflow\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "D:\anaconda\envs\tensorflow\lib\site-packages\keras\engine\training.py", line 2194, in fit_generator
generator_output = next(output_generator)
File "D:\anaconda\envs\tensorflow\lib\site-packages\keras\utils\data_utils.py", line 793, in get
six.reraise(value.class, value, value.traceback)
File "D:\anaconda\envs\tensorflow\lib\site-packages\six.py", line 693, in reraise
raise value
File "D:\anaconda\envs\tensorflow\lib\site-packages\keras\utils\data_utils.py", line 658, in _data_generator_task
generator_output = next(self._generator)
File "C:/Users/Administrator/Desktop/ssd_kerass-master/SSD_training01.py", line 206, in generate
y = self.bbox_util.assign_boxes(y)
File "C:\Users\Administrator\Desktop\ssd_kerass-master\ssd_utils.py", line 149, in assign_boxes
assignment[:, 5:-8][best_iou_mask] = boxes[best_iou_idx, 4:]

ValueError: shape mismatch: value array of shape (45,20) could not be broadcast to indexing result of shape (45,3)

[ttzhub]

训练自己的数据时，要注意数据集中已经标注的类别数。用get_data_from_XML.py中类别数与标注数一致，SSD_training.py中，类别数=标注数+1 这样就不会报错了

[marcoscleison]

Thank you @ttzhub ,
You comment helped me to setup the number of classes. However, I will translate you comment in order to help others that do not know mandarim.

When training your own data, pay attention to the number of categories already marked in the dataset. The number of categories in get_data_from_XML.py is the same as the number of labels. In SSD_training.py, the number of categories = number of labels +1 will not be reported.

Thank you very much.