Python utils.safe_log_prob() Examples

The following are 24 code examples of utils.safe_log_prob(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module utils , or try the search function .
Example #1
Source File: rebar.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #2
Source File: rebar.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #3
Source File: rebar.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #4
Source File: rebar.py    From models with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #5
Source File: rebar.py    From models with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #6
Source File: rebar.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #7
Source File: rebar.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #8
Source File: rebar.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #9
Source File: rebar.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #10
Source File: rebar.py    From object_detection_kitti with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #11
Source File: rebar.py    From object_detection_kitti with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #12
Source File: rebar.py    From hands-detection with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #13
Source File: rebar.py    From hands-detection with MIT License 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #14
Source File: rebar.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #15
Source File: rebar.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= tf.expand_dims(temperature, -1)

    if self.hparams.muprop_relaxation:
      y = tf.nn.sigmoid(x + log_alpha * tf.expand_dims(temperature/(temperature + 1), -1))
    else:
      y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #16
Source File: rebar.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def _random_sample_soft(self, log_alpha, u, layer, temperature=None):
    """Returns sampled random variables parameterized by log_alpha."""
    if temperature is None:
      temperature = self.hparams.temperature

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    x /= temperature

    if self.hparams.muprop_relaxation:
      x += temperature/(temperature + 1)*log_alpha

    y = tf.nn.sigmoid(x)

    return {
        'preactivation': x,
        'activation': y,
        'log_param': log_alpha
    }
Example #17
Source File: rebar.py    From object_detection_kitti with Apache License 2.0 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #18
Source File: rebar.py    From object_detection_with_tensorflow with MIT License 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #19
Source File: rebar.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #20
Source File: rebar.py    From hands-detection with MIT License 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #21
Source File: rebar.py    From models with Apache License 2.0 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #22
Source File: rebar.py    From Gun-Detector with Apache License 2.0 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #23
Source File: rebar.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }
Example #24
Source File: rebar.py    From yolo_v2 with Apache License 2.0 5 votes vote down vote up 
def _random_sample(self, log_alpha, u, layer):
    """Returns sampled random variables parameterized by log_alpha."""
    # Generate tied randomness for later
    if layer not in self.uniform_samples_v:
      self.uniform_samples_v[layer] = self._u_to_v(log_alpha, u)

    # Sample random variable underlying softmax/argmax
    x = log_alpha + U.safe_log_prob(u) - U.safe_log_prob(1 - u)
    samples = tf.stop_gradient(tf.to_float(x > 0))

    return {
        'preactivation': x,
        'activation': samples,
        'log_param': log_alpha,
    }