cls_loss broadcast error

[coldgemini]

this is when using custom dataset with nonuniform image sizes

File "/home/xiangyong/Workbench/RetinaNet-unsky/retinanet/core/metric.py", line 73, in update
cls_loss = np.sum(-1 * alpha * labels * np.power(1 - cls_+eps, gamma) * np.log(cls_+eps) - (1-labels)*(1-alpha) * np.power(1 - ( 1-cls_)+eps, gamma) * np.log( 1-cls_+eps))
ValueError: operands could not be broadcast together with shapes (1,20,123) (1,5,123)

[rnsandeep]

Have you changed your num_classes variable to the number of your custom dataset?
You need to change it in both pascal_voc.py file and metric.py file.