[BUG] build_tpu_model is not supported for bi-lstm-crf

[PoetCoderJun]

not support bi-lstm-crf

My code

import numpy as np
import pandas as pd
import kashgari
import re
from kashgari.embeddings import BERTEmbedding
from kashgari.tasks.labeling import BiLSTM_CRF_Model
import precess_data
from sklearn.model_selection import train_test_split
from tensorflow.python import keras
from kashgari.callbacks import EvalCallBack
if __name__ == '__main__':
    data = pd.read_excel("./data/2019data.xlsx")
    result = precess_data.get_ners_postion(data)
    result = np.array(result)
    train_x, test_x, train_y, test_y = train_test_split(result[:,0],  result[:,1], test_size=0.3, random_state=0)
    train_x = list(train_x)
    train_y = list(train_y)
    test_x = list(test_x)
    test_y = list(test_y)
    embedding = BERTEmbedding('chinese_L-12_H-768_A-12',
                                  task = kashgari.LABELING,
                                  sequence_length = 110)
    model = BiLSTM_CRF_Model(embedding)
    import os
    import kashgari
    import tensorflow as tf
    tpu_address = 'grpc://' + os.environ['COLAB_TPU_ADDR']
    strategy = tf.contrib.tpu.TPUDistributionStrategy(
        tf.contrib.cluster_resolver.TPUClusterResolver(tpu=tpu_address)
    )
    model.build_tpu_model(strategy, train_x, train_y, test_x, test_y)
    model.compile_model()
    model.fit(train_x, train_y, test_x, test_y, batch_size=20, epochs = 4)
    model.evaluate(test_x, test_y)

The output is:

WARNING: Logging before flag parsing goes to stderr.
W0724 02:31:49.620104 139957599934336 lazy_loader.py:50]
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
• https://github.com/tensorflow/io (for I/O related ops)
  If you depend on functionality not listed there, please file an issue.
  W0724 02:31:51.877970 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/initializers.py:119: calling RandomUniform.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:31:52.536731 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:1288: calling VarianceScaling.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:32:28.374124 139957599934336 bert_embedding.py:126] seq_len: 110
  W0724 02:35:18.050119 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:97: calling GlorotUniform.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:35:18.052801 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:97: calling Orthogonal.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:35:18.053946 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:97: calling Zeros.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:35:19.130405 139957599934336 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow/contrib/crf/python/ops/crf.py:567: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
  Instructions for updating:
  Please use keras.layers.RNN(cell), which is equivalent to this API
  W0724 02:35:19.214694 139957599934336 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/rnn.py:244: add_dispatch_support..wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
  Instructions for updating:
  Use tf.where in 2.0, which has the same broadcast rule as np.where
  W0724 02:35:19.365216 139957599934336 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/kashgari/tasks/base_model.py:196: tpu_model (from tensorflow.contrib.tpu.python.tpu.keras_support) is deprecated and will be removed after 2019-02-20.
  Instructions for updating:
  Switch to tf.contrib.distribute.TPUStrategy. https://www.tensorflow.org/api_docs/python/tf/contrib/distribute/DistributionStrategy
  W0724 02:35:28.360939 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:97: calling Ones.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  W0724 02:35:28.391096 139957599934336 deprecation.py:506] From /usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/init_ops.py:97: calling GlorotNormal.init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
  Instructions for updating:
  Call initializer instance with the dtype argument instead of passing it to the constructor
  FailedPreconditionError Traceback (most recent call last)
  /usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
  1355 try:
  -> 1356 return fn(*args)
  1357 except errors.OpError as e:

18 frames
FailedPreconditionError: From /job:worker/replica:0/task:0:
Error while reading resource variable layer_crf/transitions from Container: worker. This could mean that the variable was uninitialized. Not found: Resource worker/layer_crf/transitions/N10tensorflow3VarE does not exist.
[[{{node layer_crf/transitions/Read/ReadVariableOp}}]]

During handling of the above exception, another exception occurred:

FailedPreconditionError Traceback (most recent call last)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1368 pass
1369 message = error_interpolation.interpolate(message, self._graph)
-> 1370 raise type(e)(node_def, op, message)
1371
1372 def _extend_graph(self):

FailedPreconditionError: From /job:worker/replica:0/task:0:
Error while reading resource variable layer_crf/transitions from Container: worker. This could mean that the variable was uninitialized. Not found: Resource worker/layer_crf/transitions/N10tensorflow3VarE does not exist.
[[node layer_crf/transitions/Read/ReadVariableOp (defined at /usr/local/lib/python3.6/dist-packages/kashgari/layers/crf.py:80) ]]

Original stack trace for 'layer_crf/transitions/Read/ReadVariableOp':
File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py", line 16, in
app.launch_new_instance()
File "/usr/local/lib/python3.6/dist-packages/traitlets/config/application.py", line 658, in launch_instance
app.start()
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelapp.py", line 477, in start
ioloop.IOLoop.instance().start()
File "/usr/local/lib/python3.6/dist-packages/tornado/ioloop.py", line 888, in start
handler_func(fd_obj, events)
File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 450, in _handle_events
self._handle_recv()
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 480, in _handle_recv
self._run_callback(callback, msg)
File "/usr/local/lib/python3.6/dist-packages/zmq/eventloop/zmqstream.py", line 432, in _run_callback
callback(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tornado/stack_context.py", line 277, in null_wrapper
return fn(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 283, in dispatcher
return self.dispatch_shell(stream, msg)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 235, in dispatch_shell
handler(stream, idents, msg)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/kernelbase.py", line 399, in execute_request
user_expressions, allow_stdin)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/ipkernel.py", line 196, in do_execute
res = shell.run_cell(code, store_history=store_history, silent=silent)
File "/usr/local/lib/python3.6/dist-packages/ipykernel/zmqshell.py", line 533, in run_cell
return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2718, in run_cell
interactivity=interactivity, compiler=compiler, result=result)
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2822, in run_ast_nodes
if self.run_code(code, result):
File "/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py", line 2882, in run_code
exec(code_obj, self.user_global_ns, self.user_ns)
File "", line 2, in
model.build_tpu_model(strategy, train_x, train_y, test_x, test_y)
File "/usr/local/lib/python3.6/dist-packages/kashgari/tasks/base_model.py", line 195, in build_tpu_model
self.build_model_arc()
File "/usr/local/lib/python3.6/dist-packages/kashgari/tasks/labeling/models.py", line 114, in build_model_arc
output_tensor = layer_crf(tensor)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 591, in call
self._maybe_build(inputs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1881, in _maybe_build
self.build(input_shapes)
File "/usr/local/lib/python3.6/dist-packages/kashgari/layers/crf.py", line 80, in build
trainable=True)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 384, in add_weight
aggregation=aggregation)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py", line 663, in _add_variable_with_custom_getter
**kwargs_for_getter)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer_utils.py", line 155, in make_variable
shape=variable_shape if variable_shape.rank else None)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 259, in call
return cls._variable_v1_call(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 220, in _variable_v1_call
shape=shape)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 198, in
previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variable_scope.py", line 2495, in default_variable_creator
shape=shape)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/variables.py", line 263, in call
return super(VariableMetaclass, cls).call(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 460, in init
shape=shape)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 649, in _init_from_args
value = self._read_variable_op()
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/resource_variable_ops.py", line 935, in _read_variable_op
self._dtype)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/ops/gen_resource_variable_ops.py", line 587, in read_variable_op
"ReadVariableOp", resource=resource, dtype=dtype, name=name)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 3616, in create_op
op_def=op_def)
File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/ops.py", line 2005, in init
self._traceback = tf_stack.extract_stack()

[BrikerMan]

CRF layer does not support multi-GPU (#174) and TPU, you may use bi-lstm for training on TPU. We will try to make CRF layer compatible with multi-GPU and TPU.