error in own dataset when i train

hello
i genarate .lst and .rec and .idx
but when i tarin
Give me this error
Network FLOPs: 24.2G
INFO:root:loading recordio ../datasets/train.rec...
Traceback (most recent call last):
File "train.py", line 378, in
main()
File "train.py", line 375, in main
train_net(args)
File "train.py", line 243, in train_net
images_filter = config.data_images_filter,
File "/home/ml/insightface-master/recognition/image_iter.py", line 39, in __init__
s = self.imgrec.read_idx(0)
File "/usr/local/lib/python3.5/dist-packages/mxnet/recordio.py", line 313, in read_idx
self.seek(idx)
File "/usr/local/lib/python3.5/dist-packages/mxnet/recordio.py", line 275, in seek
pos = ctypes.c_size_t(self.idx[idx])
KeyError: 0
[14:51:49] src/engine/engine.cc:55: MXNet start using engine: ThreadedEnginePerDevice

please help me