when i training cicyscades dataset, the error like this

[bitwangdan]

num_images 2975 cityscape_leftImg8bit_train gt segdb loaded from ./data/cache/cityscape_leftImg8bit_train_gt_segdb.pkl append flipped images to segdb [('label', (1, 1, 768, 1024))] providing maximum shape [('data', (1, 3, 768, 1024))] [('label', (1, 1, 768, 1024))] {'data': (1L, 3L, 768L, 1024L), 'label': (1L, 1L, 768L, 1024L)} ./model/pretrained_model/resnet_v1_101 lr 0.0005 lr_epoch_diff [40.336] lr_iters [239999] Traceback (most recent call last): File "experiments/deeplab/deeplab_train_test.py", line 20, in train.main() File "experiments/deeplab/../../deeplab/train.py", line 166, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "experiments/deeplab/../../deeplab/train.py", line 160, in train_net arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch) File "experiments/deeplab/../../deeplab/core/module.py", line 984, in fit self.update_metric(eval_metric, data_batch.label) File "experiments/deeplab/../../deeplab/core/module.py", line 1076, in update_metric self._curr_module.update_metric(eval_metric, labels) File "experiments/deeplab/../../deeplab/core/module.py", line 673, in update_metric self._exec_group.update_metric(eval_metric, labels) File "experiments/deeplab/../../deeplab/core/DataParallelExecutorGroup.py", line 492, in update_metric eval_metric.update(labels, texec.outputs) File "/home/danny.wd/gitlab/mxnet-ssd/mxnet/python/mxnet/metric.py", line 294, in update metric.update(labels, preds) File "experiments/deeplab/../../deeplab/core/metric.py", line 37, in update cls = pred[keep_inds, label] IndexError: index 23 is out of bounds for axis 1 with size 19

in the .yaml files, the num_class is 19, can someone help me?

[distillation-dcf]

I met the same problem, how do you solve it? @bitwangdan