Python queue_runner_impl.start_queue_runners函数代码示例

 def test_long_eval_discard_indivisible(self):
   g = ops.Graph()
   with g.as_default():
     model = ARModel(periodicities=2,
                     num_features=1,
                     num_time_buckets=10,
                     input_window_size=2,
                     output_window_size=2)
     raw_features = {
         TrainEvalFeatures.TIMES: [[1, 3, 5, 7, 11]],
         TrainEvalFeatures.VALUES: [[[1.], [2.], [3.], [4.], [5.]]]}
     model.initialize_graph()
     raw_evaluation = model.define_loss(
         raw_features, mode=estimator_lib.ModeKeys.EVAL)
     with session.Session() as sess:
       coordinator = coordinator_lib.Coordinator()
       queue_runner_impl.start_queue_runners(sess, coord=coordinator)
       variables.global_variables_initializer().run()
       raw_evaluation_evaled = sess.run(raw_evaluation)
       self.assertAllEqual([[7, 11]],
                           raw_evaluation_evaled.prediction_times)
       for feature_name in raw_evaluation.predictions:
         self.assertAllEqual(
             [1, 2, 1],  # batch, window, num_features. The window has two cut
                         # off for the first input window and one discarded so
                         # that the remainder is divisible into output windows.
             raw_evaluation_evaled.predictions[feature_name].shape)
       coordinator.request_stop()
       coordinator.join()

 def _gap_test_template(self, times, values):
   random_model = RandomStateSpaceModel(
       state_dimension=1, state_noise_dimension=1,
       configuration=state_space_model.StateSpaceModelConfiguration(
           num_features=1))
   random_model.initialize_graph()
   input_fn = input_pipeline.WholeDatasetInputFn(
       input_pipeline.NumpyReader({
           feature_keys.TrainEvalFeatures.TIMES: times,
           feature_keys.TrainEvalFeatures.VALUES: values
       }))
   features, _ = input_fn()
   times = features[feature_keys.TrainEvalFeatures.TIMES]
   values = features[feature_keys.TrainEvalFeatures.VALUES]
   model_outputs = random_model.get_batch_loss(
       features={
           feature_keys.TrainEvalFeatures.TIMES: times,
           feature_keys.TrainEvalFeatures.VALUES: values
       },
       mode=None,
       state=math_utils.replicate_state(
           start_state=random_model.get_start_state(),
           batch_size=array_ops.shape(times)[0]))
   with self.cached_session() as session:
     variables.global_variables_initializer().run()
     coordinator = coordinator_lib.Coordinator()
     queue_runner_impl.start_queue_runners(session, coord=coordinator)
     model_outputs.loss.eval()
     coordinator.request_stop()
     coordinator.join()

  def testFeederActsLikeQueue(self):
    # Tests that a feeder acts like a queue
    feeder = feeder_lib.Feeder(
        dtypes=[dtypes_lib.string, dtypes_lib.string],
        shapes=[[], []],
        capacity=10)

    feeder.set_many_fed_tensors([
        constant_op.constant(['a0', 'a1', 'a2']),
        constant_op.constant(['b0', 'b1', 'b2'])
    ])

    out_a, out_b = feeder.get_fed_tensors()

    with self.test_session() as session:
      coord = coordinator.Coordinator()
      queue_runner_impl.start_queue_runners(session, coord=coord)

      a, b = session.run([out_a, out_b])
      self.assertEquals(b'a0', a)
      self.assertEquals(b'b0', b)
      a = session.run(out_a)  # Omit b!
      self.assertEquals(b'a1', a)
      a, b = session.run([out_a, out_b])
      self.assertEquals(b'a2', a)
      self.assertEquals(b'b2', b)  # queued together
      a, b = session.run([out_a, out_b])  # loops around
      self.assertEquals(b'a0', a)
      self.assertEquals(b'b0', b)  # queued together

    coord.request_stop()
    coord.join()

  def _test_pass_to_next(self, read_offset, step, correct_offset):
    stub_model = StubTimeSeriesModel(correct_offset=correct_offset)
    data = self._make_test_data(
        length=100 + read_offset, cut_start=None, cut_end=None, offset=100.,
        step=step)
    init_input_fn = input_pipeline.WholeDatasetInputFn(
        input_pipeline.NumpyReader(
            {k: v[:-read_offset] for k, v in data.items()}))
    result_input_fn = input_pipeline.WholeDatasetInputFn(
        input_pipeline.NumpyReader(
            {k: v[read_offset:] for k, v in data.items()}))

    chainer = state_management.ChainingStateManager(
        state_saving_interval=1)
    stub_model.initialize_graph()
    chainer.initialize_graph(model=stub_model)
    init_model_outputs = chainer.define_loss(
        model=stub_model, features=init_input_fn()[0],
        mode=estimator_lib.ModeKeys.TRAIN)
    result_model_outputs = chainer.define_loss(
        model=stub_model, features=result_input_fn()[0],
        mode=estimator_lib.ModeKeys.TRAIN)
    with self.test_session() as session:
      variables.global_variables_initializer().run()
      coordinator = coordinator_lib.Coordinator()
      queue_runner_impl.start_queue_runners(session, coord=coordinator)
      init_model_outputs.loss.eval()
      returned_loss = result_model_outputs.loss.eval()
      coordinator.request_stop()
      coordinator.join()
      return returned_loss

 def _test_initialization(self, warmup_iterations, batch_size):
   stub_model = StubTimeSeriesModel()
   data = self._make_test_data(length=20, cut_start=None, cut_end=None,
                               offset=0.)
   if batch_size == -1:
     input_fn = test_utils.AllWindowInputFn(
         input_pipeline.NumpyReader(data), window_size=10)
   else:
     input_fn = input_pipeline.RandomWindowInputFn(
         input_pipeline.NumpyReader(data),
         window_size=10,
         batch_size=batch_size)
   chainer = state_management.ChainingStateManager(
       state_saving_interval=1)
   features, _ = input_fn()
   stub_model.initialize_graph()
   chainer.initialize_graph(model=stub_model)
   model_outputs = chainer.define_loss(
       model=stub_model, features=features, mode=estimator_lib.ModeKeys.TRAIN)
   with self.test_session() as session:
     variables.global_variables_initializer().run()
     coordinator = coordinator_lib.Coordinator()
     queue_runner_impl.start_queue_runners(session, coord=coordinator)
     for _ in range(warmup_iterations):
       # Warm up saved state
       model_outputs.loss.eval()
     outputs = model_outputs.loss.eval()
     coordinator.request_stop()
     coordinator.join()
     return outputs

 def _random_window_input_fn_test_template(
     self, time_series_reader, window_size, batch_size, num_features,
     discard_out_of_order=False):
   input_fn = input_pipeline.RandomWindowInputFn(
       time_series_reader=time_series_reader,
       window_size=window_size, batch_size=batch_size)
   result, _ = input_fn()
   init_op = variables.local_variables_initializer()
   with self.cached_session() as session:
     coordinator = coordinator_lib.Coordinator()
     queue_runner_impl.start_queue_runners(session, coord=coordinator)
     session.run(init_op)
     features = session.run(result)
     coordinator.request_stop()
     coordinator.join()
   self.assertAllEqual([batch_size, window_size],
                       features[TrainEvalFeatures.TIMES].shape)
   for window_position in range(window_size - 1):
     for batch_position in range(batch_size):
       # Checks that all times are contiguous
       self.assertEqual(
           features[TrainEvalFeatures.TIMES][batch_position,
                                             window_position + 1],
           features[TrainEvalFeatures.TIMES][batch_position,
                                             window_position] + 1)
   self.assertAllEqual([batch_size, window_size, num_features],
                       features[TrainEvalFeatures.VALUES].shape)
   self.assertEqual("int64", features[TrainEvalFeatures.TIMES].dtype)
   for feature_number in range(num_features):
     self.assertAllEqual(
         features[TrainEvalFeatures.TIMES] * 2. + feature_number,
         features[TrainEvalFeatures.VALUES][:, :, feature_number])
   return features

 def _all_window_input_fn_test_template(
     self, time_series_reader, num_samples, window_size,
     original_numpy_features=None):
   input_fn = test_utils.AllWindowInputFn(
       time_series_reader=time_series_reader,
       window_size=window_size)
   features, _ = input_fn()
   init_op = variables.local_variables_initializer()
   with self.cached_session() as session:
     coordinator = coordinator_lib.Coordinator()
     queue_runner_impl.start_queue_runners(session, coord=coordinator)
     session.run(init_op)
     chunked_times, chunked_values = session.run(
         [features[TrainEvalFeatures.TIMES],
          features[TrainEvalFeatures.VALUES]])
     coordinator.request_stop()
     coordinator.join()
   self.assertAllEqual([num_samples - window_size + 1, window_size],
                       chunked_times.shape)
   if original_numpy_features is not None:
     original_times = original_numpy_features[TrainEvalFeatures.TIMES]
     original_values = original_numpy_features[TrainEvalFeatures.VALUES]
     self.assertAllEqual(original_times, numpy.unique(chunked_times))
     self.assertAllEqual(original_values[chunked_times],
                         chunked_values)

 def _equivalent_to_single_model_test_template(self, model_generator):
   with self.cached_session() as session:
     random_model = RandomStateSpaceModel(
         state_dimension=5,
         state_noise_dimension=4,
         configuration=state_space_model.StateSpaceModelConfiguration(
             dtype=dtypes.float64, num_features=1))
     random_model.initialize_graph()
     series_length = 10
     model_data = random_model.generate(
         number_of_series=1, series_length=series_length,
         model_parameters=random_model.random_model_parameters())
     input_fn = input_pipeline.WholeDatasetInputFn(
         input_pipeline.NumpyReader(model_data))
     features, _ = input_fn()
     model_outputs = random_model.get_batch_loss(
         features=features,
         mode=None,
         state=math_utils.replicate_state(
             start_state=random_model.get_start_state(),
             batch_size=array_ops.shape(
                 features[feature_keys.TrainEvalFeatures.TIMES])[0]))
     variables.global_variables_initializer().run()
     compare_outputs_evaled_fn = model_generator(
         random_model, model_data)
     coordinator = coordinator_lib.Coordinator()
     queue_runner_impl.start_queue_runners(session, coord=coordinator)
     compare_outputs_evaled = compare_outputs_evaled_fn(session)
     model_outputs_evaled = session.run(
         (model_outputs.end_state, model_outputs.predictions))
     coordinator.request_stop()
     coordinator.join()
     model_posteriors, model_predictions = model_outputs_evaled
     (_, compare_posteriors,
      compare_predictions) = compare_outputs_evaled
     (model_posterior_mean, model_posterior_var,
      model_from_time) = model_posteriors
     (compare_posterior_mean, compare_posterior_var,
      compare_from_time) = compare_posteriors
     self.assertAllClose(model_posterior_mean, compare_posterior_mean[0])
     self.assertAllClose(model_posterior_var, compare_posterior_var[0])
     self.assertAllClose(model_from_time, compare_from_time)
     self.assertEqual(sorted(model_predictions.keys()),
                      sorted(compare_predictions.keys()))
     for prediction_name in model_predictions:
       if prediction_name == "loss":
         # Chunking means that losses will be different; skip testing them.
         continue
       # Compare the last chunk to their corresponding un-chunked model
       # predictions
       last_prediction_chunk = compare_predictions[prediction_name][-1]
       comparison_values = last_prediction_chunk.shape[0]
       model_prediction = (
           model_predictions[prediction_name][0, -comparison_values:])
       self.assertAllClose(model_prediction,
                           last_prediction_chunk)

 def _input_statistics_test_template(
     self, stat_object, num_features, dtype, give_full_data,
     warmup_iterations=0, rtol=1e-6, data_length=500, chunk_size=4):
   graph = ops.Graph()
   with graph.as_default():
     numpy_dtype = dtype.as_numpy_dtype
     values = (
         (numpy.arange(data_length, dtype=numpy_dtype)[..., None]
          + numpy.arange(num_features, dtype=numpy_dtype)[None, ...])[None])
     times = 2 * (numpy.arange(data_length)[None]) - 3
     if give_full_data:
       stat_object.set_data((times, values))
     features = {TrainEvalFeatures.TIMES: times,
                 TrainEvalFeatures.VALUES: values}
     input_fn = input_pipeline.RandomWindowInputFn(
         batch_size=16, window_size=chunk_size,
         time_series_reader=input_pipeline.NumpyReader(features))
     statistics = stat_object.initialize_graph(
         features=input_fn()[0])
     with self.session(graph=graph) as session:
       variables.global_variables_initializer().run()
       coordinator = coordinator_lib.Coordinator()
       queue_runner_impl.start_queue_runners(session, coord=coordinator)
       for _ in range(warmup_iterations):
         # A control dependency should ensure that, for queue-based statistics,
         # a use of any statistic is preceded by an update of all adaptive
         # statistics.
         statistics.total_observation_count.eval()
       self.assertAllClose(
           range(num_features) + numpy.mean(numpy.arange(chunk_size))[None],
           statistics.series_start_moments.mean.eval(),
           rtol=rtol)
       self.assertAllClose(
           numpy.tile(numpy.var(numpy.arange(chunk_size))[None],
                      [num_features]),
           statistics.series_start_moments.variance.eval(),
           rtol=rtol)
       self.assertAllClose(
           numpy.mean(values[0], axis=0),
           statistics.overall_feature_moments.mean.eval(),
           rtol=rtol)
       self.assertAllClose(
           numpy.var(values[0], axis=0),
           statistics.overall_feature_moments.variance.eval(),
           rtol=rtol)
       self.assertAllClose(
           -3,
           statistics.start_time.eval(),
           rtol=rtol)
       self.assertAllClose(
           data_length,
           statistics.total_observation_count.eval(),
           rtol=rtol)
       coordinator.request_stop()
       coordinator.join()

 def testStartQueueRunnersRaisesIfNotASession(self):
   zero64 = constant_op.constant(0, dtype=dtypes.int64)
   var = variables.VariableV1(zero64)
   count_up_to = var.count_up_to(3)
   queue = data_flow_ops.FIFOQueue(10, dtypes.float32)
   init_op = variables.global_variables_initializer()
   qr = queue_runner_impl.QueueRunner(queue, [count_up_to])
   queue_runner_impl.add_queue_runner(qr)
   with self.cached_session():
     init_op.run()
     with self.assertRaisesRegexp(TypeError, "tf.Session"):
       queue_runner_impl.start_queue_runners("NotASession")

  def testExtendAfterQueueRunners(self):
    server = self._cached_server
    with session.Session(server.target) as sess:
      input_queue = input_ops.input_producer(constant_op.constant(
          [0.], dtype=dtypes.float32))
      self.assertIsNotNone(input_queue)

      var = variables.VariableV1(1., dtype=dtypes.float32, trainable=False,
                                 name="var")

      sess.run(variables.global_variables_initializer())
      queue_runner_impl.start_queue_runners(sess)
      sess.run(var.assign(3.0))

 def test_long_eval(self):
   g = ops.Graph()
   with g.as_default():
     model = ARModel(periodicities=2,
                     num_features=1,
                     num_time_buckets=10,
                     input_window_size=2,
                     output_window_size=1)
     raw_features = {
         TrainEvalFeatures.TIMES: [[1, 3, 5, 7, 11]],
         TrainEvalFeatures.VALUES: [[[1.], [2.], [3.], [4.], [5.]]]}
     chunked_features, _ = test_utils.AllWindowInputFn(
         time_series_reader=input_pipeline.NumpyReader(raw_features),
         window_size=3)()
     model.initialize_graph()
     with variable_scope.variable_scope("armodel") as scope:
       raw_evaluation = model.define_loss(
           raw_features, mode=estimator_lib.ModeKeys.EVAL)
     with variable_scope.variable_scope(scope, reuse=True):
       chunked_evaluation = model.define_loss(
           chunked_features, mode=estimator_lib.ModeKeys.EVAL)
     with session.Session() as sess:
       coordinator = coordinator_lib.Coordinator()
       queue_runner_impl.start_queue_runners(sess, coord=coordinator)
       variables.global_variables_initializer().run()
       raw_evaluation_evaled, chunked_evaluation_evaled = sess.run(
           [raw_evaluation, chunked_evaluation])
       self.assertAllEqual(chunked_evaluation_evaled.loss,
                           raw_evaluation_evaled.loss)
       last_chunk_evaluation_state = [
           state[-1, None] for state in
           chunked_evaluation_evaled.end_state]
       for last_chunk_state_member, raw_state_member in zip(
           last_chunk_evaluation_state, raw_evaluation_evaled.end_state):
         self.assertAllEqual(last_chunk_state_member, raw_state_member)
       self.assertAllEqual([[5, 7, 11]],
                           raw_evaluation_evaled.prediction_times)
       for feature_name in raw_evaluation.predictions:
         self.assertAllEqual(
             [1, 3, 1],  # batch, window, num_features. The window size has 2
                         # cut off for the first input_window.
             raw_evaluation_evaled.predictions[feature_name].shape)
         self.assertAllEqual(
             np.reshape(chunked_evaluation_evaled.predictions[feature_name],
                        [-1]),
             np.reshape(raw_evaluation_evaled.predictions[feature_name],
                        [-1]))
       coordinator.request_stop()
       coordinator.join()

 def testNotAMultiple(self):
   num_unroll = 3  # Not a divisor of value_length -
   # so padding would have been necessary.
   with self.test_session() as sess:
     with self.assertRaisesRegexp(errors_impl.InvalidArgumentError,
                                  ".*should be a multiple of: 3, but saw "
                                  "value: 4. Consider setting pad=True."):
       coord = coordinator.Coordinator()
       threads = None
       try:
         with coord.stop_on_exception():
           next_batch = sqss.batch_sequences_with_states(
               input_key=self.key,
               input_sequences=self.sequences,
               input_context=self.context,
               input_length=3,
               initial_states=self.initial_states,
               num_unroll=num_unroll,
               batch_size=self.batch_size,
               num_threads=3,
               # to enforce that we only move on to the next examples after
               # finishing all segments of the first ones.
               capacity=2,
               pad=False)
           threads = queue_runner_impl.start_queue_runners(coord=coord)
           sess.run([next_batch.key])
       except errors_impl.OutOfRangeError:
         pass
       finally:
         coord.request_stop()
         if threads is not None:
           coord.join(threads, stop_grace_period_secs=2)

 def testPandasFeeding(self):
   if not HAS_PANDAS:
     return
   with ops.Graph().as_default():
     array1 = np.arange(32)
     array2 = np.arange(32, 64)
     df = pd.DataFrame({"a": array1, "b": array2}, index=np.arange(64, 96))
     q = ff._enqueue_data(df, capacity=100)
     batch_size = 5
     dq_op = q.dequeue_many(5)
     with session.Session() as sess:
       coord = coordinator.Coordinator()
       threads = queue_runner_impl.start_queue_runners(sess=sess, coord=coord)
       for i in range(100):
         indices = [
             j % array1.shape[0]
             for j in range(batch_size * i, batch_size * (i + 1))
         ]
         expected_df_indices = df.index[indices]
         expected_rows = df.iloc[indices]
         dq = sess.run(dq_op)
         np.testing.assert_array_equal(expected_df_indices, dq[0])
         for col_num, col in enumerate(df.columns):
           np.testing.assert_array_equal(expected_rows[col].values,
                                         dq[col_num + 1])
       coord.request_stop()
       coord.join(threads)

  def test_keyed_features_filter(self):
    gfile.Glob = self._orig_glob
    lines = [
        '{"features": {"feature": {"age": {"int64_list": {"value": [2]}}}}}',
        '{"features": {"feature": {"age": {"int64_list": {"value": [0]}}}}}',
        '{"features": {"feature": {"age": {"int64_list": {"value": [1]}}}}}',
        '{"features": {"feature": {"age": {"int64_list": {"value": [0]}}}}}',
        '{"features": {"feature": {"age": {"int64_list": {"value": [3]}}}}}',
        '{"features": {"feature": {"age": {"int64_list": {"value": [5]}}}}}'
    ]
    filename = self._create_temp_file("\n".join(lines))

    batch_size = 2
    queue_capacity = 4
    name = "my_batch"
    features = {"age": parsing_ops.FixedLenFeature([], dtypes_lib.int64)}

    def filter_fn(keys, examples_json):
      del keys
      serialized = parsing_ops.decode_json_example(examples_json)
      examples = parsing_ops.parse_example(serialized, features)
      return math_ops.less(examples["age"], 2)

    with ops.Graph().as_default() as g, self.session(graph=g) as session:
      keys, inputs = graph_io._read_keyed_batch_examples_helper(
          filename,
          batch_size,
          reader=io_ops.TextLineReader,
          randomize_input=False,
          num_epochs=1,
          read_batch_size=batch_size,
          queue_capacity=queue_capacity,
          filter_fn=filter_fn,
          name=name)
      self.assertAllEqual((None,), keys.get_shape().as_list())
      self.assertAllEqual((None,), inputs.get_shape().as_list())
      session.run(variables.local_variables_initializer())

      coord = coordinator.Coordinator()
      threads = queue_runner_impl.start_queue_runners(session, coord=coord)
      # First batch of two filtered examples.
      out_keys, out_vals = session.run((keys, inputs))
      self.assertAllEqual(
          [filename.encode("utf-8") + b":2", filename.encode("utf-8") + b":3"],
          out_keys)
      self.assertAllEqual([lines[1].encode("utf-8"), lines[2].encode("utf-8")],
                          out_vals)

      # Second batch will only have one filtered example as that's the only
      # remaining example that satisfies the filtering criterion.
      out_keys, out_vals = session.run((keys, inputs))
      self.assertAllEqual([filename.encode("utf-8") + b":4"], out_keys)
      self.assertAllEqual([lines[3].encode("utf-8")], out_vals)

      # Exhausted input.
      with self.assertRaises(errors.OutOfRangeError):
        session.run((keys, inputs))

      coord.request_stop()
      coord.join(threads)