TypeError: Expected labels to be a SparseTensor

[bt9411]

HOW TO FIX THIS ?

Traceback (most recent call last):
File "train.py", line 51, in
tf.sg_train(lr=0.0001, loss=get_loss(input=inputs, target=labels, seq_len=seq_len),ep_size=data.num_batch, max_ep=50)
File "F:\Anaconda\envs\tensorflow-gpu\lib\site-packages\sugartensor\sg_main.py", line 592, in wrapper
res.append(func(opt * tf.sg_opt(gpu_index=i)))
File "train.py", line 43, in get_loss
return logit.sg_ctc(target=opt.target[opt.gpu_index], seq_len=opt.seq_len[opt.gpu_index])
File "F:\Anaconda\envs\tensorflow-gpu\lib\site-packages\sugartensor\sg_main.py", line 170, in wrapper
out = func(tensor, tf.sg_opt(kwargs))
File "F:\Anaconda\envs\tensorflow-gpu\lib\site-packages\sugartensor\sg_loss.py", line 226, in sg_ctc
ctc_merge_repeated=opt.merge, time_major=False)
File "F:\Anaconda\envs\tensorflow-gpu\lib\site-packages\tensorflow\python\ops\ctc_ops.py", line 133, in ctc_loss
raise TypeError("Expected labels to be a SparseTensor")
TypeError: Expected labels to be a SparseTensor