Python utils.center() Examples

The following are 14 code examples of utils.center(). 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 _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #2
Source File: rebar.py    From yolo_v2 with Apache License 2.0 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #3
Source File: rebar.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #4
Source File: rebar.py    From Gun-Detector with Apache License 2.0 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #5
Source File: rebar.py    From object_detection_kitti with Apache License 2.0 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #6
Source File: rebar.py    From object_detection_kitti with Apache License 2.0 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #7
Source File: rebar.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #8
Source File: rebar.py    From object_detection_with_tensorflow with MIT License 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #9
Source File: rebar.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #10
Source File: rebar.py    From g-tensorflow-models with Apache License 2.0 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #11
Source File: rebar.py    From models with Apache License 2.0 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #12
Source File: rebar.py    From models with Apache License 2.0 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal
Example #13
Source File: rebar.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
def _create_baseline(self, n_output=1, n_hidden=100,
                       is_zero_init=False,
                       collection='BASELINE'):
    # center input
    h = self._x
    if self.mean_xs is not None:
      h -= self.mean_xs

    if is_zero_init:
      initializer = init_ops.zeros_initializer()
    else:
      initializer = slim.variance_scaling_initializer()

    with slim.arg_scope([slim.fully_connected],
                        variables_collections=[collection, Q_COLLECTION],
                        trainable=False,
                        weights_initializer=initializer):
      h = slim.fully_connected(h, n_hidden, activation_fn=tf.nn.tanh)
      baseline = slim.fully_connected(h, n_output, activation_fn=None)

      if n_output == 1:
        baseline = tf.reshape(baseline, [-1])  # very important to reshape
    return baseline
Example #14
Source File: rebar.py    From multilabel-image-classification-tensorflow with MIT License 6 votes vote down vote up 
def _create_loss(self):
    # Hard loss
    logQHard, samples = self._recognition_network()
    reinforce_learning_signal, reinforce_model_grad = self._generator_network(samples, logQHard)
    logQHard = tf.add_n(logQHard)

    # REINFORCE
    learning_signal = tf.stop_gradient(U.center(reinforce_learning_signal))
    self.optimizerLoss = -(learning_signal*logQHard +
                           reinforce_model_grad)
    self.lHat = map(tf.reduce_mean, [
        reinforce_learning_signal,
        U.rms(learning_signal),
    ])

    return reinforce_learning_signal