Python testing_utils.get_test_data函数代码示例

  def test_image_classification_declarative(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=200,
          test_samples=100,
          input_shape=(8, 8, 3),
          num_classes=2)
      y_train = keras.utils.to_categorical(y_train)
      y_test = keras.utils.to_categorical(y_test)

      model = keras.models.Sequential()
      model.add(keras.layers.Conv2D(
          8, 3,
          activation='relu',
          input_shape=x_train.shape[1:]))
      model.add(keras.layers.BatchNormalization())
      model.add(keras.layers.Conv2D(
          8, 3,
          padding='same',
          activation='relu'))
      model.add(keras.layers.GlobalMaxPooling2D())
      model.add(keras.layers.Dense(y_train.shape[-1], activation='softmax'))
      model.compile(loss='categorical_crossentropy',
                    optimizer='adam',
                    metrics=['accuracy'])
      history = model.fit(x_train, y_train, epochs=10, batch_size=16,
                          validation_data=(x_test, y_test),
                          verbose=2)
      self.assertGreater(history.history['val_acc'][-1], 0.85)

  def test_video_classification_functional(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=200,
          test_samples=100,
          input_shape=(4, 8, 8, 3),
          num_classes=3)
      y_train = keras.utils.to_categorical(y_train)
      y_test = keras.utils.to_categorical(y_test)

      inputs = keras.layers.Input(shape=x_train.shape[1:])
      x = keras.layers.TimeDistributed(
          keras.layers.Conv2D(4, 3, activation='relu'))(inputs)
      x = keras.layers.BatchNormalization()(x)
      x = keras.layers.TimeDistributed(keras.layers.GlobalMaxPooling2D())(x)
      x = keras.layers.Conv1D(8, 3, activation='relu')(x)
      x = keras.layers.Flatten()(x)
      outputs = keras.layers.Dense(y_train.shape[-1], activation='softmax')(x)

      model = keras.models.Model(inputs, outputs)
      model.compile(loss='categorical_crossentropy',
                    optimizer=keras.optimizers.SGD(lr=0.01, momentum=0.8),
                    metrics=['accuracy'])
      history = model.fit(x_train, y_train, epochs=10, batch_size=16,
                          validation_data=(x_test, y_test),
                          verbose=2)
      self.assertGreater(history.history['val_acc'][-1], 0.70)

def _test_optimizer(optimizer, target=0.75):
  np.random.seed(1337)
  (x_train, y_train), _ = testing_utils.get_test_data(train_samples=1000,
                                                      test_samples=200,
                                                      input_shape=(10,),
                                                      num_classes=2)
  y_train = keras.utils.to_categorical(y_train)
  model = _get_model(x_train.shape[1], 20, y_train.shape[1])
  model.compile(loss='categorical_crossentropy',
                optimizer=optimizer,
                metrics=['accuracy'])
  history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
  assert history.history['acc'][-1] >= target
  config = keras.optimizers.serialize(optimizer)
  optim = keras.optimizers.deserialize(config)
  new_config = keras.optimizers.serialize(optim)
  new_config['class_name'] = new_config['class_name'].lower()
  assert config == new_config

  # Test constraints.
  model = keras.models.Sequential()
  dense = keras.layers.Dense(10,
                             input_shape=(x_train.shape[1],),
                             kernel_constraint=lambda x: 0. * x + 1.,
                             bias_constraint=lambda x: 0. * x + 2.,
                             activation='relu')
  model.add(dense)
  model.add(keras.layers.Dense(y_train.shape[1], activation='softmax'))
  model.compile(loss='categorical_crossentropy',
                optimizer=optimizer,
                metrics=['accuracy'])
  model.train_on_batch(x_train[:10], y_train[:10])
  kernel, bias = dense.get_weights()
  np.testing.assert_allclose(kernel, 1., atol=1e-3)
  np.testing.assert_allclose(bias, 2., atol=1e-3)

  def test_vector_classification_shared_model(self):
    # Test that functional models that feature internal updates
    # and internal losses can be shared.
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=200,
          test_samples=100,
          input_shape=(10,),
          num_classes=2)
      y_train = keras.utils.to_categorical(y_train)
      y_test = keras.utils.to_categorical(y_test)

      inputs = keras.layers.Input(x_train.shape[1:])
      x = keras.layers.Dense(16,
                             activation='relu',
                             kernel_regularizer=keras.regularizers.l2(1e-5),
                             bias_regularizer=keras.regularizers.l2(1e-5),
                             input_shape=x_train.shape[1:])(inputs)
      x = keras.layers.BatchNormalization()(x)
      base_model = keras.models.Model(inputs, x)

      x = keras.layers.Input(x_train.shape[1:])
      y = base_model(x)
      y = keras.layers.Dense(y_train.shape[-1], activation='softmax')(y)
      model = keras.models.Model(x, y)
      model.compile(loss='categorical_crossentropy',
                    optimizer='rmsprop',
                    metrics=['accuracy'])
      history = model.fit(x_train, y_train, epochs=10, batch_size=16,
                          validation_data=(x_test, y_test),
                          verbose=2)
      self.assertGreater(history.history['val_acc'][-1], 0.85)

  def test_invalid_loss_or_metrics(self):
    num_classes = 5
    train_samples = 1000
    test_samples = 1000
    input_dim = 5

    with self.test_session():
      model = keras.models.Sequential()
      model.add(keras.layers.Dense(10, input_shape=(input_dim,)))
      model.add(keras.layers.Activation('relu'))
      model.add(keras.layers.Dense(num_classes))
      model.add(keras.layers.Activation('softmax'))
      model.compile(loss='categorical_crossentropy', optimizer='rmsprop')
      np.random.seed(1337)
      (x_train, y_train), (_, _) = testing_utils.get_test_data(
          train_samples=train_samples,
          test_samples=test_samples,
          input_shape=(input_dim,),
          num_classes=num_classes)
      with self.assertRaises(ValueError):
        model.fit(x_train, y_train)

      with self.assertRaises(ValueError):
        model.fit(x_train, np.concatenate([y_train, y_train], axis=-1))

      with self.assertRaises(TypeError):
        model.compile(loss='categorical_crossentropy',
                      optimizer='rmsprop',
                      metrics=set(0))

      with self.assertRaises(RuntimeError):
        model.compile(loss=None,
                      optimizer='rmsprop')

  def test_vector_classification_declarative(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=200,
          test_samples=100,
          input_shape=(10,),
          num_classes=2)
      y_train = keras.utils.to_categorical(y_train)
      y_test = keras.utils.to_categorical(y_test)

      model = keras.models.Sequential([
          keras.layers.Dense(16,
                             activation='relu',
                             input_shape=x_train.shape[1:]),
          keras.layers.Dropout(0.1),
          keras.layers.Dense(y_train.shape[-1], activation='softmax')
      ])
      model.compile(loss='categorical_crossentropy',
                    optimizer='rmsprop',
                    metrics=['accuracy'])
      history = model.fit(x_train, y_train, epochs=10, batch_size=16,
                          validation_data=(x_test, y_test),
                          verbose=2)
      self.assertGreater(history.history['val_acc'][-1], 0.85)

  def test_TerminateOnNaN(self):
    np.random.seed(1337)
    (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
        train_samples=TRAIN_SAMPLES,
        test_samples=TEST_SAMPLES,
        input_shape=(INPUT_DIM,),
        num_classes=NUM_CLASSES)

    y_test = keras.utils.to_categorical(y_test)
    y_train = keras.utils.to_categorical(y_train)
    cbks = [keras.callbacks.TerminateOnNaN()]
    model = keras.models.Sequential()
    initializer = keras.initializers.Constant(value=1e5)
    for _ in range(5):
      model.add(keras.layers.Dense(2,
                                   input_dim=INPUT_DIM,
                                   activation='relu',
                                   kernel_initializer=initializer))
    model.add(keras.layers.Dense(NUM_CLASSES))
    model.compile(loss='mean_squared_error',
                  optimizer='rmsprop')

    history = model.fit(x_train, y_train, batch_size=BATCH_SIZE,
                        validation_data=(x_test, y_test),
                        callbacks=cbks, epochs=20)
    loss = history.history['loss']
    assert len(loss) == 1
    assert loss[0] == np.inf

  def test_LearningRateScheduler(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=TRAIN_SAMPLES,
          test_samples=TEST_SAMPLES,
          input_shape=(INPUT_DIM,),
          num_classes=NUM_CLASSES)
      y_test = keras.utils.to_categorical(y_test)
      y_train = keras.utils.to_categorical(y_train)
      model = keras.models.Sequential()
      model.add(
          keras.layers.Dense(
              NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
      model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
      model.compile(
          loss='categorical_crossentropy',
          optimizer='sgd',
          metrics=['accuracy'])

      cbks = [keras.callbacks.LearningRateScheduler(lambda x: 1. / (1. + x))]
      model.fit(
          x_train,
          y_train,
          batch_size=BATCH_SIZE,
          validation_data=(x_test, y_test),
          callbacks=cbks,
          epochs=5,
          verbose=0)
      assert (float(keras.backend.get_value(model.optimizer.lr)) - 0.2
             ) < keras.backend.epsilon()

def get_data():
  (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
      train_samples=10,
      test_samples=10,
      input_shape=(DATA_DIM,),
      num_classes=NUM_CLASSES)
  y_train = keras.utils.to_categorical(y_train, NUM_CLASSES)
  y_test = keras.utils.to_categorical(y_test, NUM_CLASSES)
  return (x_train, y_train), (x_test, y_test)

  def test_stop_training_csv(self):
    # Test that using the CSVLogger callback with the TerminateOnNaN callback
    # does not result in invalid CSVs.
    np.random.seed(1337)
    tmpdir = self.get_temp_dir()
    self.addCleanup(shutil.rmtree, tmpdir)

    with self.test_session():
      fp = os.path.join(tmpdir, 'test.csv')
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=TRAIN_SAMPLES,
          test_samples=TEST_SAMPLES,
          input_shape=(INPUT_DIM,),
          num_classes=NUM_CLASSES)

      y_test = keras.utils.to_categorical(y_test)
      y_train = keras.utils.to_categorical(y_train)
      cbks = [keras.callbacks.TerminateOnNaN(), keras.callbacks.CSVLogger(fp)]
      model = keras.models.Sequential()
      for _ in range(5):
        model.add(keras.layers.Dense(2, input_dim=INPUT_DIM, activation='relu'))
      model.add(keras.layers.Dense(NUM_CLASSES, activation='linear'))
      model.compile(loss='mean_squared_error',
                    optimizer='rmsprop')

      def data_generator():
        i = 0
        max_batch_index = len(x_train) // BATCH_SIZE
        tot = 0
        while 1:
          if tot > 3 * len(x_train):
            yield (np.ones([BATCH_SIZE, INPUT_DIM]) * np.nan,
                   np.ones([BATCH_SIZE, NUM_CLASSES]) * np.nan)
          else:
            yield (x_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE],
                   y_train[i * BATCH_SIZE: (i + 1) * BATCH_SIZE])
          i += 1
          tot += 1
          i %= max_batch_index

      history = model.fit_generator(data_generator(),
                                    len(x_train) // BATCH_SIZE,
                                    validation_data=(x_test, y_test),
                                    callbacks=cbks,
                                    epochs=20)
      loss = history.history['loss']
      assert len(loss) > 1
      assert loss[-1] == np.inf or np.isnan(loss[-1])

      values = []
      with open(fp) as f:
        for x in csv.reader(f):
          values.append(x)
      assert 'nan' in values[-1], 'The last epoch was not logged.'

  def test_EarlyStopping(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=TRAIN_SAMPLES,
          test_samples=TEST_SAMPLES,
          input_shape=(INPUT_DIM,),
          num_classes=NUM_CLASSES)
      y_test = keras.utils.to_categorical(y_test)
      y_train = keras.utils.to_categorical(y_train)
      model = keras.models.Sequential()
      model.add(
          keras.layers.Dense(
              NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
      model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
      model.compile(
          loss='categorical_crossentropy',
          optimizer='rmsprop',
          metrics=['accuracy'])
      mode = 'max'
      monitor = 'val_acc'
      patience = 0
      cbks = [
          keras.callbacks.EarlyStopping(
              patience=patience, monitor=monitor, mode=mode)
      ]
      model.fit(
          x_train,
          y_train,
          batch_size=BATCH_SIZE,
          validation_data=(x_test, y_test),
          callbacks=cbks,
          epochs=20,
          verbose=0)

      mode = 'auto'
      monitor = 'val_acc'
      patience = 2
      cbks = [
          keras.callbacks.EarlyStopping(
              patience=patience, monitor=monitor, mode=mode)
      ]
      model.fit(
          x_train,
          y_train,
          batch_size=BATCH_SIZE,
          validation_data=(x_test, y_test),
          callbacks=cbks,
          epochs=20,
          verbose=0)

def assert_regression_works(reg):
  np.random.seed(42)
  (x_train, y_train), (x_test, _) = testing_utils.get_test_data(
      train_samples=TRAIN_SAMPLES,
      test_samples=TEST_SAMPLES,
      input_shape=(INPUT_DIM,),
      num_classes=NUM_CLASSES)

  reg.fit(x_train, y_train, batch_size=BATCH_SIZE, epochs=EPOCHS)

  score = reg.score(x_train, y_train, batch_size=BATCH_SIZE)
  assert np.isscalar(score) and np.isfinite(score)

  preds = reg.predict(x_test, batch_size=BATCH_SIZE)
  assert preds.shape == (TEST_SAMPLES,)

  def test_ReduceLROnPlateau(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=TRAIN_SAMPLES,
          test_samples=TEST_SAMPLES,
          input_shape=(INPUT_DIM,),
          num_classes=NUM_CLASSES)
      y_test = keras.utils.to_categorical(y_test)
      y_train = keras.utils.to_categorical(y_train)

      def make_model():
        np.random.seed(1337)
        model = keras.models.Sequential()
        model.add(
            keras.layers.Dense(
                NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
        model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))

        model.compile(
            loss='categorical_crossentropy',
            optimizer=keras.optimizers.SGD(lr=0.1),
            metrics=['accuracy'])
        return model

      model = make_model()
      # This should reduce the LR after the first epoch (due to high epsilon).
      cbks = [
          keras.callbacks.ReduceLROnPlateau(
              monitor='val_loss',
              factor=0.1,
              epsilon=10,
              patience=1,
              cooldown=5)
      ]
      model.fit(
          x_train,
          y_train,
          batch_size=BATCH_SIZE,
          validation_data=(x_test, y_test),
          callbacks=cbks,
          epochs=5,
          verbose=0)
      self.assertAllClose(
          float(keras.backend.get_value(model.optimizer.lr)),
          0.01,
          atol=1e-4)

def _test_optimizer(optimizer, target=0.75):
  np.random.seed(1337)
  (x_train, y_train), _ = testing_utils.get_test_data(train_samples=1000,
                                                      test_samples=200,
                                                      input_shape=(10,),
                                                      num_classes=2)
  y_train = keras.utils.to_categorical(y_train)
  model = _get_model(x_train.shape[1], 20, y_train.shape[1])
  model.compile(loss='categorical_crossentropy',
                optimizer=optimizer,
                metrics=['accuracy'])
  history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
  assert history.history['acc'][-1] >= target
  config = keras.optimizers.serialize(optimizer)
  optim = keras.optimizers.deserialize(config)
  new_config = keras.optimizers.serialize(optim)
  new_config['class_name'] = new_config['class_name'].lower()
  assert config == new_config

  def test_LambdaCallback(self):
    with self.test_session():
      np.random.seed(1337)
      (x_train, y_train), (x_test, y_test) = testing_utils.get_test_data(
          train_samples=TRAIN_SAMPLES,
          test_samples=TEST_SAMPLES,
          input_shape=(INPUT_DIM,),
          num_classes=NUM_CLASSES)
      y_test = keras.utils.to_categorical(y_test)
      y_train = keras.utils.to_categorical(y_train)
      model = keras.models.Sequential()
      model.add(
          keras.layers.Dense(
              NUM_HIDDEN, input_dim=INPUT_DIM, activation='relu'))
      model.add(keras.layers.Dense(NUM_CLASSES, activation='softmax'))
      model.compile(
          loss='categorical_crossentropy',
          optimizer='sgd',
          metrics=['accuracy'])

      # Start an arbitrary process that should run during model
      # training and be terminated after training has completed.
      def target():
        while True:
          pass

      p = multiprocessing.Process(target=target)
      p.start()
      cleanup_callback = keras.callbacks.LambdaCallback(
          on_train_end=lambda logs: p.terminate())

      cbks = [cleanup_callback]
      model.fit(
          x_train,
          y_train,
          batch_size=BATCH_SIZE,
          validation_data=(x_test, y_test),
          callbacks=cbks,
          epochs=5,
          verbose=0)
      p.join()
      assert not p.is_alive()