def _get_feed_dict(self, xs, ys, *args, **kwargs):
if self.reg == 'dropout':
if args:
kp = args[0]
else:
kp = kwargs['keep_prob']
if not hasattr(self, '_keep_prob'):
self._keep_prob = tfnn.constant(kp)
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys,
self.keep_prob_placeholder: kp
}
elif self.reg == 'l2':
if args:
l2_value = args[0]
else:
l2_value = kwargs['l2_value']
if not hasattr(self, '_l2_value'):
self._l2_value = tfnn.constant(l2_value)
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys,
self.l2_placeholder: l2_value
}
else:
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys
}
return _feed_dict
def _get_feed_dict(self, xs, ys, *args, **kwargs):
if self.reg == 'dropout':
if args:
kp = args[0]
else:
kp = kwargs['keep_prob']
if not hasattr(self, '_keep_prob'):
self._keep_prob = tfnn.constant(kp)
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys,
self.keep_prob_placeholder: kp
}
elif self.reg == 'l2':
if args:
l2_value = args[0]
else:
l2_value = kwargs['l2_value']
if not hasattr(self, '_l2_value'):
self._l2_value = tfnn.constant(l2_value)
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys,
self.l2_placeholder: l2_value
}
else:
_feed_dict = {
self.data_placeholder: xs,
self.target_placeholder: ys
}
return _feed_dict
def set_learning_rate(self, lr, exp_decay=None):
"""
:param lr:
:param exp_decay: a dictionary like dict(decay_steps=None, decay_rate=None, staircase=False, name=None),
otherwise None.
:return:
"""
if isinstance(exp_decay, dict):
if 'decay_steps' not in exp_decay:
raise KeyError(
'Set decay_steps in exp_decay=dict(decay_steps)')
if 'decay_rate' not in exp_decay:
raise KeyError('Set decay_steps in exp_decay=dict(decay_rate)')
if 'staircase' not in exp_decay:
exp_decay['staircase'] = False
if 'name' not in exp_decay:
exp_decay['name'] = None
self._lr = tfnn.train.exponential_decay(
lr,
self.global_step,
decay_steps=exp_decay['decay_steps'],
decay_rate=exp_decay['decay_rate'],
staircase=exp_decay['staircase'],
name=exp_decay['name'])
else:
self._lr = tfnn.constant(lr)
tfnn.scalar_summary('learning_rate', self._lr)
def __init__(self, network, ):
self.network = network
if isinstance(self.network, tfnn.ClfNetwork):
with tfnn.name_scope('accuracy'):
with tfnn.name_scope('correct_prediction'):
correct_prediction = tfnn.equal(tfnn.argmax(network.predictions, 1),
tfnn.argmax(network.target_placeholder, 1), name='correct_prediction')
with tfnn.name_scope('accuracy'):
self.accuracy = tfnn.reduce_mean(tfnn.cast(correct_prediction, tfnn.float32), name='accuracy')
tfnn.scalar_summary('accuracy', self.accuracy)
elif isinstance(self.network, tfnn.RegNetwork):
self.first_time_lm = True
self.first_time_soc = True
with tfnn.name_scope('r2_score'):
with tfnn.name_scope('ys_mean'):
ys_mean = tfnn.reduce_mean(network.target_placeholder, reduction_indices=[0], name='ys_mean')
with tfnn.name_scope('total_sum_squares'):
ss_tot = tfnn.reduce_sum(tfnn.square(network.target_placeholder - ys_mean),
reduction_indices=[0], name='total_sum_squares')
# ss_reg = np.sum(np.square(predictions-ys_mean), axis=0)
with tfnn.name_scope('residual_sum_squares'):
ss_res = tfnn.reduce_sum(tfnn.square(network.target_placeholder - network.predictions),
reduction_indices=[0], name='residual_sum_squares')
with tfnn.name_scope('coefficient_of_determination'):
self.r2_score = tfnn.sub(tfnn.constant(1, dtype=tfnn.float32), (ss_res / ss_tot)[0],
name='coefficient_of_determination')
tfnn.scalar_summary('r2_score', self.r2_score)
def set_learning_rate(self, lr, exp_decay=None):
"""
:param lr:
:param exp_decay: a dictionary like dict(decay_steps=None, decay_rate=None, staircase=False, name=None),
otherwise None.
:return:
"""
if isinstance(exp_decay, dict):
if 'decay_steps' not in exp_decay:
raise KeyError('Set decay_steps in exp_decay=dict(decay_steps)')
if 'decay_rate' not in exp_decay:
raise KeyError('Set decay_steps in exp_decay=dict(decay_rate)')
if 'staircase' not in exp_decay:
exp_decay['staircase'] = False
if 'name' not in exp_decay:
exp_decay['name'] = None
self._lr = tfnn.train.exponential_decay(lr, self.global_step,
decay_steps=exp_decay['decay_steps'],
decay_rate=exp_decay['decay_rate'],
staircase=exp_decay['staircase'],
name=exp_decay['name'])
else:
self._lr = tfnn.constant(lr)
tfnn.scalar_summary('learning_rate', self._lr)
def __init__(
self,
network,
):
self.network = network
if isinstance(self.network, tfnn.ClfNetwork):
with tfnn.name_scope('accuracy'):
with tfnn.name_scope('correct_prediction'):
correct_prediction = tfnn.equal(
tfnn.argmax(network.predictions, 1),
tfnn.argmax(network.target_placeholder, 1),
name='correct_prediction')
with tfnn.name_scope('accuracy'):
self.accuracy = tfnn.reduce_mean(tfnn.cast(
correct_prediction, tfnn.float32),
name='accuracy')
tfnn.scalar_summary('accuracy', self.accuracy)
elif isinstance(self.network, tfnn.RegNetwork):
self.first_time_lm = True
self.first_time_soc = True
with tfnn.name_scope('r2_score'):
with tfnn.name_scope('ys_mean'):
ys_mean = tfnn.reduce_mean(network.target_placeholder,
reduction_indices=[0],
name='ys_mean')
with tfnn.name_scope('total_sum_squares'):
ss_tot = tfnn.reduce_sum(
tfnn.square(network.target_placeholder - ys_mean),
reduction_indices=[0],
name='total_sum_squares')
# ss_reg = np.sum(np.square(predictions-ys_mean), axis=0)
with tfnn.name_scope('residual_sum_squares'):
ss_res = tfnn.reduce_sum(
tfnn.square(network.target_placeholder -
network.predictions),
reduction_indices=[0],
name='residual_sum_squares')
with tfnn.name_scope('coefficient_of_determination'):
self.r2_score = tfnn.sub(tfnn.constant(1, dtype=tfnn.float32),
(ss_res / ss_tot)[0],
name='coefficient_of_determination')
tfnn.scalar_summary('r2_score', self.r2_score)
def _bias_variable(self, shape):
initial = tfnn.constant(0.1, shape=shape, dtype=self.input_dtype, name='biases')
return tfnn.Variable(initial)
def _bias_variable(self, shape):
initial = tfnn.constant(0.1, shape=shape, dtype=self.input_dtype, name='biases')
return tfnn.Variable(initial)