本文整理汇总了Python中tensorflow.keras.backend.cast方法的典型用法代码示例。如果您正苦于以下问题:Python backend.cast方法的具体用法?Python backend.cast怎么用?Python backend.cast使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.keras.backend
的用法示例。
在下文中一共展示了backend.cast方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: call
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def call(self, x, mask=None):
"""Layer functionality."""
# Skip integration of input spikes in membrane potential. Directly
# transmit new spikes. The output psp is nonzero wherever there has
# been an input spike at any time during simulation.
input_psp = MaxPooling2D.call(self, x)
if self.spiketrain is not None:
new_spikes = tf.math.logical_xor(
k.greater(input_psp, 0), k.greater(self.last_spiketimes, 0))
self.add_update([(self.spiketrain,
self.time * k.cast(new_spikes, k.floatx()))])
psp = self.get_psp(input_psp)
return k.cast(psp, k.floatx())
示例2: tversky_loss
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def tversky_loss(y_true, y_pred, smooth=0.000001):
# Define alpha and beta
alpha = 0.5
beta = 0.5
# Calculate Tversky for each class
axis = identify_axis(y_true.get_shape())
tp = K.sum(y_true * y_pred, axis=axis)
fn = K.sum(y_true * (1-y_pred), axis=axis)
fp = K.sum((1-y_true) * y_pred, axis=axis)
tversky_class = (tp + smooth)/(tp + alpha*fn + beta*fp + smooth)
# Sum up classes to one score
tversky = K.sum(tversky_class, axis=[-1])
# Identify number of classes
n = K.cast(K.shape(y_true)[-1], 'float32')
# Return Tversky
return n-tversky
#-----------------------------------------------------#
# Tversky & Crossentropy loss #
#-----------------------------------------------------#
示例3: cat_acc
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def cat_acc(y_true, y_pred):
"""Keras loss function for sparse_categorical_accuracy.
:param y_true: tensor of true class labels.
:param y_pred: class output scores from network.
:returns: categorical accuracy.
"""
# sparse_categorical_accuracy is broken in keras 2.2.4
# https://github.com/keras-team/keras/issues/11348#issuecomment-439969957
# this is taken from e59570ae
from tensorflow.keras import backend as K
# reshape in case it's in shape (num_samples, 1) instead of (num_samples,)
if K.ndim(y_true) == K.ndim(y_pred):
y_true = K.squeeze(y_true, -1)
# convert dense predictions to labels
y_pred_labels = K.argmax(y_pred, axis=-1)
y_pred_labels = K.cast(y_pred_labels, K.floatx())
return K.cast(K.equal(y_true, y_pred_labels), K.floatx())
示例4: _find_maxima
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def _find_maxima(x, coordinate_scale=1, confidence_scale=255.0):
x = K.cast(x, K.floatx())
col_max = K.max(x, axis=1)
row_max = K.max(x, axis=2)
maxima = K.max(col_max, 1)
maxima = K.expand_dims(maxima, -2) / confidence_scale
cols = K.cast(K.argmax(col_max, -2), K.floatx())
rows = K.cast(K.argmax(row_max, -2), K.floatx())
cols = K.expand_dims(cols, -2) * coordinate_scale
rows = K.expand_dims(rows, -2) * coordinate_scale
maxima = K.concatenate([cols, rows, maxima], -2)
return maxima
示例5: _preprocess_conv2d_input
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def _preprocess_conv2d_input(x, data_format):
"""Transpose and cast the input before the conv2d.
# Arguments
x: input tensor.
data_format: string, `"channels_last"` or `"channels_first"`.
# Returns
A tensor.
"""
if dtype(x) == "float64":
x = tf.cast(x, "float32")
if data_format == "channels_first":
# TF uses the last dimension as channel dimension,
# instead of the 2nd one.
# TH input shape: (samples, input_depth, rows, cols)
# TF input shape: (samples, rows, cols, input_depth)
x = tf.transpose(x, (0, 2, 3, 1))
return x
示例6: recall
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def recall(y_true, y_pred):
"""Precision for foreground pixels.
Calculates pixelwise recall TP/(TP + FN).
"""
# count true positives
truth = K.round(K.clip(y_true, K.epsilon(), 1))
pred_pos = K.round(K.clip(y_pred, K.epsilon(), 1))
true_pos = K.sum(K.cast(K.all(K.stack([truth, pred_pos], axis=2), axis=2),
dtype='float64'))
truth_ct = K.sum(K.round(K.clip(y_true, K.epsilon(), 1)))
if truth_ct == 0:
return 0
recall = true_pos/truth_ct
return recall
示例7: loss
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def loss(self, y_true, y_pred):
""" categorical crossentropy loss """
if self.crop_indices is not None:
y_true = utils.batch_gather(y_true, self.crop_indices)
y_pred = utils.batch_gather(y_pred, self.crop_indices)
if self.use_float16:
y_true = K.cast(y_true, 'float16')
y_pred = K.cast(y_pred, 'float16')
# scale and clip probabilities
# this should not be necessary for softmax output.
y_pred /= K.sum(y_pred, axis=-1, keepdims=True)
y_pred = K.clip(y_pred, K.epsilon(), 1)
# compute log probability
log_post = K.log(y_pred) # likelihood
# loss
loss = - y_true * log_post
# weighted loss
if self.weights is not None:
loss *= self.weights
if self.vox_weights is not None:
loss *= self.vox_weights
# take the total loss
# loss = K.batch_flatten(loss)
mloss = K.mean(K.sum(K.cast(loss, 'float32'), -1))
tf.verify_tensor_all_finite(mloss, 'Loss not finite')
return mloss
示例8: loss_function
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def loss_function(self, inputs, outputs):
total_loss = 0
total_metrics = {}
if len(self._tasks) == 1:
inputs = (inputs,)
try:
batch_size = K.cast(tf.shape(inputs[0]['primary'])[0], K.floatx())
except KeyError:
batch_size = K.cast(tf.shape(inputs[0]['first']['primary'])[0], K.floatx())
for input_, output, task in zip(inputs, outputs, self._tasks):
loss, metrics = task.loss_function(input_, output)
loss = tf.check_numerics(loss, 'loss from {}'.format(task.__class__.__name__))
for name, value in metrics.items():
metrics[name] = tf.check_numerics(value, 'metric {}'.format(name))
total_loss += loss
total_metrics.update(metrics)
total_loss *= batch_size
for key in total_metrics:
total_metrics[key] *= batch_size
total_metrics['batch_size'] = batch_size
return total_loss, total_metrics
示例9: piecewise_linear
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def piecewise_linear(t, schedule):
"""分段线性函数
其中schedule是形如{1000: 1, 2000: 0.1}的字典,
表示 t ∈ [0, 1000]时,输出从0均匀增加至1,而
t ∈ [1000, 2000]时,输出从1均匀降低到0.1,最后
t > 2000时,保持0.1不变。
"""
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
示例10: adjusted_score
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def adjusted_score(hyper_model, delta, metric_function=None):
def score(y_true, y_pred):
y_t_rank = len(y_true.shape.as_list())
y_p_rank = len(y_pred.shape.as_list())
y_t_last_dim = y_true.shape.as_list()[-1]
y_p_last_dim = y_pred.shape.as_list()[-1]
is_binary = y_p_last_dim == 1
is_sparse_categorical = (
y_t_rank < y_p_rank or y_t_last_dim == 1 and y_p_last_dim > 1)
if isinstance(metric_function, six.string_types):
if metric_function in ["accuracy", "acc"]:
if is_binary:
metric = binary_accuracy(y_true, y_pred)
elif is_sparse_categorical:
metric = sparse_categorical_accuracy(y_true, y_pred)
else:
metric = categorical_accuracy(y_true, y_pred)
else:
metric = categorical_accuracy(y_true, y_pred)
else:
metric = metric_function(y_true, y_pred)
return K.cast(metric * (1.0 + delta), K.floatx())
if not metric_function:
metric_function = "accuracy"
return score
示例11: trial_size_metric
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def trial_size_metric(trial_size):
def trial(y_true, y_pred): # pylint: disable=unused-argument
return K.cast(trial_size, K.floatx())
return trial
示例12: stochastic_round_po2
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def stochastic_round_po2(x):
"""Performs stochastic rounding for the power of two."""
# TODO(hzhuang): test stochastic_round_po2 and constraint.
# because quantizer is applied after constraint.
y = tf.abs(x)
eps = tf.keras.backend.epsilon()
log2 = tf.keras.backend.log(2.0)
x_log2 = tf.round(tf.keras.backend.log(y + eps) / log2)
po2 = tf.cast(pow(2.0, tf.cast(x_log2, dtype="float32")), dtype="float32")
left_val = tf.where(po2 > y, x_log2 - 1, x_log2)
right_val = tf.where(po2 > y, x_log2, x_log2 + 1)
# sampling in [2**left_val, 2**right_val].
minval = 2 ** left_val
maxval = 2 ** right_val
val = tf.random.uniform(tf.shape(y), minval=minval, maxval=maxval)
# use y as a threshold to keep the probabliy [2**left_val, y, 2**right_val]
# so that the mean value of the sample should be y
x_po2 = tf.where(y < val, left_val, right_val)
"""
x_log2 = stochastic_round(tf.keras.backend.log(y + eps) / log2)
sign = tf.sign(x)
po2 = (
tf.sign(x) *
tf.cast(pow(2.0, tf.cast(x_log2, dtype="float32")), dtype="float32")
)
"""
return x_po2
示例13: call
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def call(self, inputs, **kwargs):
return K.cast(K.argmin(inputs, axis=1), dtype=K.floatx())
示例14: update_neurons
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def update_neurons(self):
"""Update neurons according to activation function."""
# Update membrane potentials.
new_mem = self.get_new_mem()
# Generate spikes.
if hasattr(self, 'activation_str') \
and self.activation_str == 'softmax':
output_spikes = self.softmax_activation(new_mem)
else:
output_spikes = self.linear_activation(new_mem)
# Reset membrane potential after spikes.
self.set_reset_mem(new_mem, output_spikes)
# Store refractory period after spikes.
if hasattr(self, 'activation_str') \
and self.activation_str == 'softmax':
# We do not constrain softmax output neurons.
new_refrac = tf.identity(self.refrac_until)
else:
new_refrac = tf.where(k.not_equal(output_spikes, 0),
k.ones_like(output_spikes) *
(self.time + self.tau_refrac),
self.refrac_until)
self.add_update([(self.refrac_until, new_refrac)])
if self.spiketrain is not None:
self.add_update([(self.spiketrain, self.time * k.cast(
k.not_equal(output_spikes, 0), k.floatx()))])
# Compute post-synaptic potential.
psp = self.get_psp(output_spikes)
return k.cast(psp, k.floatx())
示例15: linear_activation
# 需要导入模块: from tensorflow.keras import backend [as 别名]
# 或者: from tensorflow.keras.backend import cast [as 别名]
def linear_activation(self, mem):
"""Linear activation."""
return k.cast(k.greater_equal(mem, self.v_thresh), k.floatx())