当我尝试将张量流内置CTC丢失函数（https://www.tensorflow.org/versions/r0.10/api_docs/python/nn/conectionist_temporal_classification__ctc_）应用于SynthText数据集时，我在训练期间遇到了运行时错误。 http://www.robots.ox.ac.uk/~vgg/data/scenetext/ 它说＆＃34;没有足够的时间用于目标转换序列（必需：4，可用：0）＆＃34;。 以下是环境的一些信息：tensorflow版本＆＃39; 0.12.0-rc0＆＃39;。
我能够将phyorflow内置CTC应用于Synth90K数据集，性能卓越。
似乎SynthText数据集不能与tensorflow内置CTC编译，但Synth90K数据集可以编译。
请查找错误消息作为参考
step 980, loss = 50.17 (92.1 examples/sec; 0.695 sec/batch)
W tensorflow/core/framework/op_kernel.cc:975] Invalid argument: Not enough time for target transition sequence (required: 4, available: 0), skipping data instance in batch: 28
Traceback (most recent call last):
File "multi-gpu-train.py", line 305, in
tf.app.run()
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "multi-gpu-train.py", line 301, in main
train()
File "multi-gpu-train.py", line 270, in train
_, loss_value = sess.run([train_op, loss])
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 766, in run
run_metadata_ptr)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 964, in _run
feed_dict_string, options, run_metadata)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1014, in _do_run
target_list, options, run_metadata)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1034, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Not enough time for target transition sequence (required: 4, available: 0), skipping data instance in batch: 28
[[Node: tower_0/CTCLoss = CTCLoss[ctc_merge_repeated=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/cpu:0"](tower_0/transpose_2/_555, tower_0/Where, tower_0/sub_2/_557, tower_0/Sum_1/_559)]]
Caused by op u'tower_0/CTCLoss', defined at:
File "multi-gpu-train.py", line 305, in
tf.app.run()
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 43, in run
sys.exit(main(sys.argv[:1] + flags_passthrough))
File "multi-gpu-train.py", line 301, in main
train()
File "multi-gpu-train.py", line 179, in train
loss,logits_op,images,labels = tower_loss(scope)
File "multi-gpu-train.py", line 79, in tower_loss
_ = network2.loss(logits,images, labels)
File "/home/ubuntu/experiments/network2_dev/network2.py", line 61, in loss
out = tf.nn.ctc_loss(logit, to_sparse(y), seq_len, time_major=False)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/ctc_ops.py", line 145, in ctc_loss
ctc_merge_repeated=ctc_merge_repeated)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_ctc_ops.py", line 164, in _ctc_loss
name=name)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 759, in apply_op
op_def=op_def)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2240, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/ubuntu/tensorflow/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1128, in init
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): Not enough time for target transition sequence (required: 4, available: 0), skipping data instance in batch: 28
[[Node: tower_0/CTCLoss = CTCLoss[ctc_merge_repeated=true, preprocess_collapse_repeated=false, _device="/job:localhost/replica:0/task:0/cpu:0"](tower_0/transpose_2/_555, tower_0/Where, tower_0/sub_2/_557, tower_0/Sum_1/_559)]]