Unable to execute the example given in the documentation

Hi! I simply put together the code snippets to execute the example given in the README as follows:

import os

import anago
from anago.utils import download
from anago.reader import load_data_and_labels
#from keras import backend as K

x_train, y_train = load_data_and_labels('train.txt')
x_valid, y_valid = load_data_and_labels('valid.txt')
x_test, y_test = load_data_and_labels('test.txt')

model = anago.Sequence()
model.train(x_train, y_train, x_valid, y_valid)

model.eval(x_test, y_test)
#K.clear_session()

words = 'President Obama is speaking at the White House.'.split()
model.analyze(words)

However, I am getting the following error during Epoch 10 (Apologies for the long message but I thought embedding the entire stack trace would help:: _``` Epoch 10/15 702/703 [============================>.] - ETA: 0s - loss: 59.00882018-05-30 09:42:27.923763: W tensorflow/core/framework/op_kernel.cc:1318] OP_REQUIRES failed at tensor_array_ops.cc:497 : Invalid argument: Tried to read from index -1 but array size is: 0 Traceback (most recent call last): File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1322, in _do_call return fn(*args) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1307, in _run_fn options, feed_dict, fetch_list, target_list, run_metadata) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1409, in _call_tf_sessionrun run_metadata) 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: training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@training/Adam/gradients/loss/chain_crf_1_loss/transpose_grad/transpose"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, loss/chain_crf_1_loss/TensorArrayUnstack/range, training/Adam/gradients/loss/chain_crf_1_loss/while/TensorArrayReadV3/Enter_1_grad/b_acc_3)]]

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "download_model.py", line 13, in model.train(x_train, y_train, x_valid, y_valid) File "/home/fussili/.local/lib/python3.5/site-packages/anago/wrapper.py", line 50, in train trainer.train(x_train, y_train, x_valid, y_valid) File "/home/fussili/.local/lib/python3.5/site-packages/anago/trainer.py", line 51, in train callbacks=callbacks) File "/home/fussili/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, kwargs) File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 2230, in fit_generator class_weight=class_weight) File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 1883, in train_on_batch outputs = self.train_function(ins) File "/home/fussili/.local/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2482, in call self.session_kwargs) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 900, in run run_metadata_ptr) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1135, in _run feed_dict_tensor, options, run_metadata) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1316, in _do_run run_metadata) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/client/session.py", line 1335, 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: training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@training/Adam/gradients/loss/chain_crf_1_loss/transpose_grad/transpose"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, loss/chain_crf_1_loss/TensorArrayUnstack/range, training/Adam/gradients/loss/chain_crf_1_loss/while/TensorArrayReadV3/Enter_1_grad/b_acc_3)]]

Caused by op 'training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3', defined at: File "download_model.py", line 13, in model.train(x_train, y_train, x_valid, y_valid) File "/home/fussili/.local/lib/python3.5/site-packages/anago/wrapper.py", line 50, in train trainer.train(x_train, y_train, x_valid, y_valid) File "/home/fussili/.local/lib/python3.5/site-packages/anago/trainer.py", line 51, in train callbacks=callbacks) File "/home/fussili/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(*args, *kwargs) File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 2080, in fit_generator self._make_train_function() File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 992, in _make_train_function loss=self.total_loss) File "/home/fussili/.local/lib/python3.5/site-packages/keras/legacy/interfaces.py", line 91, in wrapper return func(args, *kwargs) File "/home/fussili/.local/lib/python3.5/site-packages/keras/optimizers.py", line 445, in get_updates grads = self.get_gradients(loss, params) File "/home/fussili/.local/lib/python3.5/site-packages/keras/optimizers.py", line 78, in get_gradients grads = K.gradients(loss, params) File "/home/fussili/.local/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2519, in gradients return tf.gradients(loss, variables, colocate_gradients_with_ops=True) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 494, in gradients gate_gradients, aggregation_method, stop_gradients) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 636, in _GradientsHelper lambda: grad_fn(op, out_grads)) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 385, in _MaybeCompile return grad_fn() # Exit early File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gradients_impl.py", line 636, in lambda: grad_fn(op, *out_grads)) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_grad.py", line 186, in _TensorArrayScatterGrad grad = g.gather(indices) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 910, in gather return self._implementation.gather(indices, name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 305, in gather element_shape=element_shape) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 6018, in tensor_array_gather_v3 flow_in=flow_in, dtype=dtype, element_shape=element_shape, name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper op_def=op_def) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 3392, in create_op op_def=op_def) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/framework/ops.py", line 1718, in init self._traceback = self._graph._extract_stack() # pylint: disable=protected-access

...which was originally created as op 'loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3', defined at: File "download_model.py", line 13, in model.train(x_train, y_train, x_valid, y_valid) [elided 0 identical lines from previous traceback] File "/home/fussili/.local/lib/python3.5/site-packages/anago/wrapper.py", line 50, in train trainer.train(x_train, y_train, x_valid, y_valid) File "/home/fussili/.local/lib/python3.5/site-packages/anago/trainer.py", line 38, in train optimizer=Adam(lr=self.training_config.learning_rate), File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 830, in compile sample_weight, mask) File "/home/fussili/.local/lib/python3.5/site-packages/keras/engine/training.py", line 429, in weighted score_array = fn(y_true, y_pred) File "/home/fussili/.local/lib/python3.5/site-packages/anago/layers.py", line 322, in loss return chain_crf_loss(y_true, y_pred, self.U, self.b_start, self.b_end, mask) File "/home/fussili/.local/lib/python3.5/site-packages/anago/layers.py", line 66, in chain_crf_loss return sparse_chain_crf_loss(y_sparse, x, U, b_start, b_end, mask) File "/home/fussili/.local/lib/python3.5/site-packages/anago/layers.py", line 58, in sparse_chain_crf_loss energy -= free_energy0(x, U, mask) File "/home/fussili/.local/lib/python3.5/site-packages/anago/layers.py", line 124, in free_energy0 mask) File "/home/fussili/.local/lib/python3.5/site-packages/anago/layers.py", line 146, in forward last, values, = K.rnn(_forward_step, inputs, initial_states) File "/home/fussili/.local/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 2695, in rnn input_ta = input_ta.unstack(inputs) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py", line 118, in wrapped return _add_should_use_warning(fn(*args, kwargs)) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 944, in unstack return self._implementation.unstack(value, name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py", line 118, in wrapped return _add_should_use_warning(fn(*args, *kwargs)) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 333, in unstack indices=math_ops.range(0, num_elements), value=value, name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py", line 118, in wrapped return _add_should_use_warning(fn(args, kwargs)) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/tensor_array_ops.py", line 349, in scatter name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 6590, in tensor_array_scatter_v3 flow_in=flow_in, name=name) File "/home/fussili/.local/lib/python3.5/site-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper 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: training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGatherV3 = TensorArrayGatherV3[_class=["loc:@training/Adam/gradients/loss/chain_crf_1_loss/transpose_grad/transpose"], dtype=DT_FLOAT, element_shape=, _device="/job:localhost/replica:0/task:0/device:CPU:0"](training/Adam/gradients/loss/chain_crf_1_loss/TensorArrayUnstack/TensorArrayScatter/TensorArrayScatterV3_grad/TensorArrayGrad/TensorArrayGradV3, loss/chain_crf_1_loss/TensorArrayUnstack/range, training/Adam/gradients/loss/chain_crf_1_loss/while/TensorArrayReadV3/Enter_1_grad/b_acc_3)]]

Hironsan / anago

Unable to execute the example given in the documentation #64