train_semseg.py labelweights[l - 1]

[wuwenxuan0226]

In line 268,

            for l in range(NUM_CLASSES):
                iou_per_class_str += 'class %s weight: %.3f, IoU: %.3f \n' % (
                    seg_label_to_cat[l] + ' ' * (14 - len(seg_label_to_cat[l])), labelweights[l - 1],
                    total_correct_class[l] / float(total_iou_deno_class[l]))

I think labelweights[l - 1] should be labelweights[l]. In line 249, np.histogram(batch_label, range(NUM_CLASSES + 1)) will return an array which size is 13, although use range(NUM_CLASSES + 1).

[hahaha1014]

I have the same doubts, have you solved it?

[wuwenxuan0226]

@hahaha1014

I have the same doubts, have you solved it?

just use labelweights[l]