def bernoulli_loss_with_logits(self, x_gt, y_target):
x_f = tfutils.flatten(x_gt)
y_f = tfutils.flatten(y_target)
return tf.reduce_mean(
tf.reduce_sum(tf.nn.sigmoid_cross_entropy_with_logits(labels=x_f,
logits=y_f),
axis=1))
def bernoulli_loss(self, x_gt, y_target):
x_f = tfutils.flatten(x_gt)
y_f = tfutils.flatten(y_target)
return -tf.reduce_mean(
tf.reduce_sum(x_f * tf.log(1e-10 + y_f) +
(1 - x_f) * tf.log(1e-10 + 1 - y_f),
axis=1))
def gaussian_loss(self, x_gt, y_target, sigma_r):
x_f = tfutils.flatten(x_gt)
y_f = tfutils.flatten(y_target)
sigma_r_f = tfutils.flatten(
sigma_r
) # we assume implicitly that network predicts sigma squared (for numerical stability)
# Thus **2 are missing in the equation below
return tf.reduce_mean(
tf.reduce_sum(0.5 * tf.log(2 * np.pi * (sigma_r_f)) +
tf.divide(tf.square((x_f - y_f)), 2 * (sigma_r_f)),
axis=1))
def KL_two_gauss_with_diag_cov(self, mu0, sigma0, mu1, sigma1):
sigma0_fs = tf.square(tfutils.flatten(sigma0))
sigma1_fs = tf.square(tfutils.flatten(sigma1))
logsigma0_fs = tf.log(sigma0_fs + 1e-10)
logsigma1_fs = tf.log(sigma1_fs + 1e-10)
mu0_f = tfutils.flatten(mu0)
mu1_f = tfutils.flatten(mu1)
return tf.reduce_mean(0.5 * tf.reduce_sum(
tf.divide(sigma0_fs + tf.square(mu1_f - mu0_f),
sigma1_fs + 1e-10) + logsigma1_fs - logsigma0_fs - 1,
axis=1))
def dense_layer(bottom,
name,
hidden_units=512,
activation=tf.nn.relu,
weight_init='he_normal',
add_bias=True):
'''
Dense a.k.a. fully connected layer
'''
bottom_flat = utils.flatten(bottom)
bottom_rhs_dim = utils.get_rhs_dim(bottom_flat)
weight_shape = [bottom_rhs_dim, hidden_units]
bias_shape = [hidden_units]
with tf.variable_scope(name):
weights = get_weight_variable(weight_shape,
name='W',
type=weight_init,
regularize=True)
op = tf.matmul(bottom_flat, weights)
biases = None
if add_bias:
biases = get_bias_variable(bias_shape, name='b')
op = tf.nn.bias_add(op, biases)
op = activation(op)
# Add Tensorboard summaries
_add_summaries(op, weights, biases)
return op
def dense_layer(bottom,
name,
hidden_units=512,
activation=STANDARD_NONLINEARITY,
normalisation=tfnorm.batch_norm,
normalise_post_activation=False,
dropout_p=None,
weight_init='he_normal',
add_bias=True,
**kwargs):
'''
Dense a.k.a. fully connected layer
'''
bottom_flat = utils.flatten(bottom)
bottom_rhs_dim = utils.get_rhs_dim(bottom_flat)
weight_shape = [bottom_rhs_dim, hidden_units]
bias_shape = [hidden_units]
with tf.variable_scope(name):
weights = utils.get_weight_variable(weight_shape,
name='W',
type=weight_init,
regularize=True)
op = tf.matmul(bottom_flat, weights)
biases = None
if add_bias:
biases = utils.get_bias_variable(bias_shape, name='b')
op = tf.nn.bias_add(op, biases)
if not normalise_post_activation:
op = activation(normalisation(op, **kwargs))
else:
op = normalisation(activation(op), **kwargs)
if dropout_p is not None:
op = dropout(op, keep_prob=dropout_p, **kwargs)
# Add Tensorboard summaries
_add_summaries(op, weights, biases)
return op
def dense_layer(bottom,
name,
hidden_units=512,
activation=tf.nn.relu,
weight_init='he_normal'):
'''
Dense a.k.a. fully connected layer
'''
bottom_flat = utils.flatten(bottom)
bottom_rhs_dim = utils.get_rhs_dim(bottom_flat)
weight_shape = [bottom_rhs_dim, hidden_units]
bias_shape = [hidden_units]
with tf.name_scope(name):
if weight_init == 'he_normal':
N = bottom_rhs_dim
weights = _weight_variable_he_normal(weight_shape,
N,
name=name + '_w')
elif weight_init == 'simple':
weights = _weight_variable_simple(weight_shape, name=name + '_w')
else:
raise ValueError('Unknown weight initialisation method %s' %
weight_init)
biases = _bias_variable(bias_shape, name=name + '_b')
op = tf.matmul(bottom_flat, weights)
op = tf.nn.bias_add(op, biases)
op = activation(op)
# Tensorboard variables
tf.summary.histogram(weights.name, weights)
tf.summary.histogram(biases.name, biases)
tf.summary.histogram(op.op.name + '/activations', op)
return op
