Unimplemented: TensorArray has size zero about sequence_tagging

[gaoxiangyu369]

11:28:01.244383: W tensorflow/core/framework/op_kernel.cc:1152] Unimplemented: TensorArray has size zero, but element shape is not fully defined. Currently only static shapes are supported when packing zero-size TensorArrays.
[[Node: train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@rnn/TensorArray_1"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/cpu:0"](train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, rnn/TensorArrayUnstack/range, train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/gradient_flow)]]
2018-05-16 11:28:01.244397: W tensorflow/core/framework/op_kernel.cc:1152] Unimplemented: TensorArray has size zero, but element shape is not fully defined. Currently only static shapes are supported when packing zero-size TensorArrays.
[[Node: train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@rnn/TensorArray_1"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/cpu:0"](train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, rnn/TensorArrayUnstack/range, train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/gradient_flow)]]
Traceback (most recent call last):
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1039, in _do_call
return fn(*args)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
status, run_metadata)
File "/Users/shaun/anaconda3/lib/python3.6/contextlib.py", line 88, in exit
next(self.gen)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.UnimplementedError: TensorArray has size zero, but element shape is not fully defined. Currently only static shapes are supported when packing zero-size TensorArrays.
[[Node: train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@rnn/TensorArray_1"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/cpu:0"](train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, rnn/TensorArrayUnstack/range, train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/gradient_flow)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "train.py", line 26, in
main()
File "train.py", line 23, in main
model.train(train, dev)
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/base_model.py", line 121, in train
score = self.run_epoch(train, dev, epoch)
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/ner_model.py", line 290, in run_epoch
[self.train_op, self.loss, self.merged], feed_dict=fd)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.UnimplementedError: TensorArray has size zero, but element shape is not fully defined. Currently only static shapes are supported when packing zero-size TensorArrays.
[[Node: train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@rnn/TensorArray_1"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/cpu:0"](train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, rnn/TensorArrayUnstack/range, train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/gradient_flow)]]

Caused by op 'train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3', defined at:
File "train.py", line 26, in
main()
File "train.py", line 12, in main
model.build()
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/ner_model.py", line 227, in build
self.config.clip)
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/base_model.py", line 58, in add_train_op
self.train_op = optimizer.minimize(loss)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 315, in minimize
grad_loss=grad_loss)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 386, in compute_gradients
colocate_gradients_with_ops=colocate_gradients_with_ops)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 560, in gradients
grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 368, in _MaybeCompile
return grad_fn() # Exit early
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gradients_impl.py", line 560, in
grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_grad.py", line 186, in _TensorArrayScatterGrad
grad = g.gather(indices)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 328, in gather
element_shape=element_shape)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 2244, in _tensor_array_gather_v3
element_shape=element_shape, name=name)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1228, in init
self._traceback = _extract_stack()

...which was originally created as op 'rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3', defined at:
File "train.py", line 26, in
main()
[elided 0 identical lines from previous traceback]
File "train.py", line 12, in main
model.build()
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/ner_model.py", line 223, in build
self.add_loss_op()
File "/Users/shaun/Desktop/name_tag/sequence_tagging/model/ner_model.py", line 203, in add_loss_op
self.logits, self.labels, self.sequence_lengths)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/crf/python/ops/crf.py", line 156, in crf_log_likelihood
log_norm = crf_log_norm(inputs, sequence_lengths, transition_params)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/contrib/crf/python/ops/crf.py", line 123, in crf_log_norm
dtype=dtypes.float32)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 553, in dynamic_rnn
dtype=dtype)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 671, in dynamic_rnn_loop
for ta, input in zip(input_ta, flat_input))
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/rnn.py", line 671, in
for ta, input_ in zip(input_ta, flat_input))
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 381, in unstack
indices=math_ops.range(0, num_elements), value=value, name=name)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 409, in scatter
name=name)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 2510, in _tensor_array_scatter_v3
name=name)
File "/Users/shaun/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)

UnimplementedError (see above for traceback): TensorArray has size zero, but element shape is not fully defined. Currently only static shapes are supported when packing zero-size TensorArrays.
[[Node: train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@rnn/TensorArray_1"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/cpu:0"](train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, rnn/TensorArrayUnstack/range, train_step/gradients/rnn/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/gradient_flow)]]

[guillaumegenthial]

Too old, closing!