Process finished with exit code 134(interrupted by signal 6:SIGABRT)

DeepSpeech
#1

when i added the code snippet decoded, _ = decode_with_lm(logit, seq_len, merge_repeated=False, beam_width=1024) i ran the program in the pycharm.
the result i got is Process finished with exit code 134(interrupted by signal 6:SIGABRT),i checked the shape of logit,and the second dimension is equal to seq_len,namely batch_size.i also print the computer resource usage using top command,cpu and memory were ok.
here is my code example:

def decode_audio():
    batch_size = 3
    n_mfcc = 39
    indata = get_mfcc()
    input_data = tf.placeholder(dtype=tf.float32, shape=[batch_size, None, n_mfcc])
   seq_len = tf.reduce_sum(
    tf.cast(tf.not_equal(tf.reduce_sum(input_data, reduction_indices=2), 0.), tf.int32), reduction_indices=1)
    decoded, _= decode_with_lm(tf.transpose(input_data,[1,0,2]), seq_len, merge_repeated=False, beam_width=10)
    print(decoded[0])
    with tf.Session() as sess:
         sess.run(tf.global_variables_initializer())
         idx = sess.run(decoded[0],feed_dict={input_data:indata})
         print(idx)

when i ran the code,it gave me exit code 134.details are followed:

SparseTensor(indices=Tensor("CTCBeamSearchDecoderWithLM:0", shape=(?, 2), dtype=int64), values=Tensor("CTCBeamSearchDecoderWithLM:1", shape=(?,), dtype=int64), dense_shape=Tensor("CTCBeamSearchDecoderWithLM:2", shape=(2,), dtype=int64))

2018-08-27 10:23:08.727349: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-08-27 10:23:08.727602: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1208] Found device 0 with properties:
name: GeForce GTX 1070 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.683
pciBusID: 0000:01:00.0
totalMemory: 7.93GiB freeMemory: 7.58GiB
2018-08-27 10:23:08.727615: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1308] Adding visible gpu devices: 0
2018-08-27 10:23:08.899022: I tensorflow/core/common_runtime/gpu/gpu_device.cc:989] Creating TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 7315 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1070 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)

Process finished with exit code 134 (interrupted by signal 6: SIGABRT)

so any thought about the problem?

note:
i want to add the LM module to my own speech recognition model,not DeepSpeech.