Python backend.constant方法代碼示例

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def build(self, input_shape):
        assert len(input_shape) >= 2
        layer_kwargs = dict(
            kernel_initializer=self.kernel_initializer,
            bias_initializer=self.bias_initializer,
            kernel_regularizer=self.kernel_regularizer,
            bias_regularizer=self.bias_regularizer,
            kernel_constraint=self.kernel_constraint,
            bias_constraint=self.bias_constraint
        )

        self.mlp = Sequential([
            Dense(channels, self.mlp_activation, **layer_kwargs)
            for channels in self.mlp_hidden
        ] + [Dense(self.channels, self.activation, use_bias=self.use_bias, **layer_kwargs)])

        if self.epsilon is None:
            self.eps = self.add_weight(shape=(1,),
                                       initializer='zeros',
                                       name='eps')
        else:
            # If epsilon is given, keep it constant
            self.eps = K.constant(self.epsilon)

        self.built = True 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_binary_auto():
  """Test binary auto scale quantizer."""

  np.random.seed(42)
  N = 1000000
  m_list = [1.0, 0.1, 0.01, 0.001]

  for m in m_list:
    x = np.random.uniform(-m, m, (N, 10)).astype(K.floatx())
    x = K.constant(x)

    quantizer = binary(alpha="auto")
    q = K.eval(quantizer(x))

    result = get_weight_scale(quantizer, q)
    expected = m / 2.0
    logging.info("expect %s", expected)
    logging.info("result %s", result)
    assert_allclose(result, expected, rtol=0.02) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_binary_auto_po2():
  """Test binary auto_po2 scale quantizer."""

  np.random.seed(42)
  N = 1000000
  m_list = [1.0, 0.1, 0.01, 0.001]

  for m in m_list:
    x = np.random.uniform(-m, m, (N, 10)).astype(K.floatx())
    x = K.constant(x)

    quantizer_ref = binary(alpha="auto")
    quantizer = binary(alpha="auto_po2")

    q_ref = K.eval(quantizer_ref(x))
    q = K.eval(quantizer(x))

    ref = get_weight_scale(quantizer_ref, q_ref)

    expected = np.power(2.0, np.round(np.log2(ref)))
    result = get_weight_scale(quantizer, q)

    assert_allclose(result, expected, rtol=0.0001) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_ternary_auto():
  """Test ternary auto scale quantizer."""

  np.random.seed(42)
  N = 1000000
  m_list = [1.0, 0.1, 0.01, 0.001]

  for m in m_list:
    x = np.random.uniform(-m, m, (N, 10)).astype(K.floatx())
    x = K.constant(x)

    quantizer = ternary(alpha="auto")
    q = K.eval(quantizer(x))

    d = m/3.0
    result = np.mean(get_weight_scale(quantizer, q))
    expected = (m + d) / 2.0
    assert_allclose(result, expected, rtol=0.02) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_stochastic_ternary(bound, alpha, temperature, expected_values, expected_scale):
  np.random.seed(42)
  K.set_learning_phase(1)

  n = 1000

  x = np.random.uniform(-bound, bound, size=(n, 10))
  x = np.sort(x, axis=1)

  s = stochastic_ternary(alpha=alpha, temperature=temperature)

  y = K.eval(s(K.constant(x)))
  scale = K.eval(s.scale).astype(np.float32)[0]

  ty = np.zeros_like(s)
  for i in range(n):
    ty = ty + (y[i] / scale)

  result = (ty/n).astype(np.float32)

  assert_allclose(result, expected_values, atol=0.1)
  assert_allclose(scale, expected_scale, rtol=0.1) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def __init__(self, learning_rate=0.001, beta_1=0.9, beta_2=0.999,
                 epsilon=None, decay=0., amsgrad=False,
                 model=None, zero_penalties=True, batch_size=32,
                 total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, name="AdamW", **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)
        eta_t = kwargs.pop('eta_t', 1.)

        super(AdamW, self).__init__(name, **kwargs)
        self._set_hyper('learning_rate', kwargs.get('lr', learning_rate))
        self._set_hyper('decay', self._initial_decay)
        self._set_hyper('beta_1', beta_1)
        self._set_hyper('beta_2', beta_2)

        self.eta_min = K.constant(eta_min, name='eta_min')
        self.eta_max = K.constant(eta_max, name='eta_max')
        self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
        self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')
        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.init_verbose = init_verbose
        self.use_cosine_annealing = use_cosine_annealing
        self.epsilon = epsilon or backend_config.epsilon()
        self.amsgrad = amsgrad

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = kwargs.get('lr', learning_rate)  # to print lr_mult setup
        self._updates_processed = 0  # to track num calls to '_resource_apply_...'
        self._init_notified = False
        self._init_lr = kwargs.get('lr', learning_rate) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def call(self, inputs):
        F = K.int_shape(inputs)[-1]
        minkowski_prod_mat = np.eye(F)
        minkowski_prod_mat[-1, -1] = -1.
        minkowski_prod_mat = K.constant(minkowski_prod_mat)
        output = K.dot(inputs, minkowski_prod_mat)
        output = K.dot(output, K.transpose(inputs))
        output = K.clip(output, -10e9, -1.)

        if self.activation is not None:
            output = self.activation(output)

        return output 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def build(self, input_shape):
        assert len(input_shape) >= 2
        if self.trainable:
            self.beta = self.add_weight(shape=(1,), initializer='ones', name='beta')
        else:
            self.beta = K.constant(1.)
        self.built = True 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def piecewise_linear(t, schedule):
    """分段線性函數
    其中schedule是形如{1000: 1, 2000: 0.1}的字典，
    表示 t ∈ [0, 1000]時，輸出從0均勻增加至1，而
    t ∈ [1000, 2000]時，輸出從1均勻降低到0.1，最後
    t > 2000時，保持0.1不變。
    """
    schedule = sorted(schedule.items())
    if schedule[0][0] != 0:
        schedule = [(0, 0.0)] + schedule

    x = K.constant(schedule[0][1], dtype=K.floatx())
    t = K.cast(t, K.floatx())
    for i in range(len(schedule)):
        t_begin = schedule[i][0]
        x_begin = x
        if i != len(schedule) - 1:
            dx = schedule[i + 1][1] - schedule[i][1]
            dt = schedule[i + 1][0] - schedule[i][0]
            slope = 1.0 * dx / dt
            x = schedule[i][1] + slope * (t - t_begin)
        else:
            x = K.constant(schedule[i][1], dtype=K.floatx())
        x = K.switch(t >= t_begin, x, x_begin)

    return x 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def get_weights(layer):
  weights = layer.get_weights()
  out = copy.deepcopy(weights)
  for j, weight in enumerate(weights):
    if hasattr(layer, "get_quantizers") and layer.get_quantizers()[j]:
      out[j] = K.eval(
          layer.get_quantizers()[j](K.constant(weight)))

  return out 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_stochastic_binary():
  np.random.seed(42)
  K.set_learning_phase(1)

  x = np.random.uniform(-0.01, 0.01, size=10)
  x = np.sort(x)

  s = stochastic_binary(alpha="auto_po2")

  ty = np.zeros_like(s)
  ts = 0.0

  n = 1000

  for _ in range(n):
    y = K.eval(s(K.constant(x)))
    scale = K.eval(s.scale)[0]
    ts = ts + scale
    ty = ty + (y / scale)

  result = (ty/n).astype(np.float32)
  scale = np.array([ts/n])

  expected = np.array(
      [-1., -1., -1., -0.852, 0.782, 0.768, 0.97, 0.978, 1.0, 1.0]
  ).astype(np.float32)
  expected_scale = np.array([0.003906])

  assert_allclose(result, expected, atol=0.1)
  assert_allclose(scale, expected_scale, rtol=0.1) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_output_shape(dummy_data, make_model):
  # pylint: disable=redefined-outer-name
  data, _ = dummy_data
  data = K.constant(data)
  model = make_model
  l = model.get_layer(LAYER_NAME)

  actual_output_shape = l(data).shape
  expected_output_shape = l.compute_output_shape(data.shape)
  np.testing.assert_equal(expected_output_shape, actual_output_shape) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def test_output_shape(dummy_data, make_model):
  # Disable the redefined-outer-name violation in this function
  # pylint: disable=redefined-outer-name
  data, _ = dummy_data
  data = K.constant(data)
  input_shape = data.shape

  model = make_model

  actual_output_shape = model(data).shape
  expected_output_shape = model.compute_output_shape(input_shape)

  np.testing.assert_equal(expected_output_shape, actual_output_shape) 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def _smooth_labels(y_true, label_smoothing):
    label_smoothing = K.constant(label_smoothing, dtype=K.floatx())
    return y_true * (1.0 - label_smoothing) + 0.5 * label_smoothing 

# 需要導入模塊: from tensorflow.keras import backend [as 別名]
# 或者: from tensorflow.keras.backend import constant [as 別名]
def yolo3_head(feats, anchors, num_classes, input_shape, calc_loss=False):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[..., ::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[..., ::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs