def dnn(x):
with tf.name_scope('Layer1'):
W1 = tf.Variable(tf.random_normal([784, 256]), name="W1")
b1 = tf.Variable(tf.random_normal([256]), name="b1")
x = tf.nn.tanh(tf.add(tf.matmul(x, W1), b1))
# Add this `tanh` op to activations collection or monitoring
tf.add_to_collection(tf.GraphKeys.ACTIVATIONS, x)
# Add weights regularizer (Regul. summary automatically added)
tflearn.add_weights_regularizer(W1, 'L2', weight_decay=0.001)
with tf.name_scope('Layer2'):
W2 = tf.Variable(tf.random_normal([256, 256]), name="W2")
b2 = tf.Variable(tf.random_normal([256]), name="b2")
x = tf.nn.tanh(tf.add(tf.matmul(x, W2), b2))
# Add this `tanh` op to activations collection or monitoring
tf.add_to_collection(tf.GraphKeys.ACTIVATIONS, x)
# Add weights regularizer (Regul. summary automatically added)
tflearn.add_weights_regularizer(W2, 'L2', weight_decay=0.001)
with tf.name_scope('Layer3'):
W3 = tf.Variable(tf.random_normal([256, 10]), name="W3")
b3 = tf.Variable(tf.random_normal([10]), name="b3")
x = tf.add(tf.matmul(x, W3), b3)
return x
def test_regularizer(self):
# Bulk Tests
with tf.Graph().as_default():
x = tf.placeholder("float", [None, 4])
W = tf.Variable(tf.random_normal([4, 4]))
x = tf.nn.tanh(tf.matmul(x, W))
tflearn.add_weights_regularizer(W, 'L2', weight_decay=0.001)
def dnn(x):
with tf.name_scope('Layer1'):
W1 = tf.Variable(tf.random_normal([784, 256]), name="W1")
b1 = tf.Variable(tf.random_normal([256]), name="b1")
x = tf.nn.tanh(tf.add(tf.matmul(x, W1), b1))
# Add this `tanh` op to activations collection or monitoring
tf.add_to_collection(tf.GraphKeys.ACTIVATIONS, x)
# Add weights regularizer (Regul. summary automatically added)
tflearn.add_weights_regularizer(W1, 'L2', weight_decay=0.001)
with tf.name_scope('Layer2'):
W2 = tf.Variable(tf.random_normal([256, 256]), name="W2")
b2 = tf.Variable(tf.random_normal([256]), name="b2")
x = tf.nn.tanh(tf.add(tf.matmul(x, W2), b2))
# Add this `tanh` op to activations collection or monitoring
tf.add_to_collection(tf.GraphKeys.ACTIVATIONS, x)
# Add weights regularizer (Regul. summary automatically added)
tflearn.add_weights_regularizer(W2, 'L2', weight_decay=0.001)
with tf.name_scope('Layer3'):
W3 = tf.Variable(tf.random_normal([256, 10]), name="W3")
b3 = tf.Variable(tf.random_normal([10]), name="b3")
x = tf.add(tf.matmul(x, W3), b3)
return x
def test_regularizer(self):
# Bulk Tests
with tf.Graph().as_default():
x = tf.placeholder("float", [None, 4])
W = tf.Variable(tf.random_normal([4, 4]))
x = tf.nn.tanh(tf.matmul(x, W))
tflearn.add_weights_regularizer(W, 'L2', weight_decay=0.001)
def variable(name, shape=None, dtype=tf.float32, initializer=None,
regularizer=None, trainable=True, collections=None, device='',
restore=True):
""" variable.
Instantiate a new variable.
Arguments:
name: `str`. A name for this variable.
shape: list of `int`. The variable shape (optional).
dtype: `type`. The variable data type.
initializer: `str` or `Tensor`. The variable initialization. (See
tflearn.initializations for references).
regularizer: `str` or `Tensor`. The variable regularizer. (See
tflearn.losses for references).
trainable: `bool`. If True, this variable weights will be trained.
collections: `str`. A collection to add the new variable to (optional).
device: `str`. Device ID to store the variable. Default: '/cpu:0'.
restore: `bool`. Restore or not this variable when loading a
pre-trained model (Only compatible with tflearn pre-built
training functions).
Returns:
A Variable.
"""
if isinstance(initializer, str):
initializer = tflearn.initializations.get(initializer)()
# Remove shape param if initializer is a Tensor
if not callable(initializer) and isinstance(initializer, tf.Tensor):
shape = None
if isinstance(regularizer, str):
regularizer = tflearn.losses.get(regularizer)
with tf.device(device):
try:
var = tf.get_variable(name, shape=shape, dtype=dtype,
initializer=initializer,
regularizer=regularizer,
trainable=trainable,
collections=collections)
# Fix for old TF versions
except Exception as e:
var = tf.get_variable(name, shape=shape, dtype=dtype,
initializer=initializer,
trainable=trainable,
collections=collections)
if regularizer is not None:
tflearn.add_weights_regularizer(var, regularizer)
if not restore:
tf.add_to_collection(tf.GraphKeys.EXCL_RESTORE_VARS, var)
return var
def variable(name, shape=None, dtype=tf.float32, initializer=None,
regularizer=None, trainable=True, collections=None, device='',
restore=True):
""" variable.
Instantiate a new variable.
Arguments:
name: `str`. A name for this variable.
shape: list of `int`. The variable shape (optional).
dtype: `type`. The variable data type.
initializer: `str` or `Tensor`. The variable initialization. (See
tflearn.initializations for references).
regularizer: `str` or `Tensor`. The variable regularizer. (See
tflearn.losses for references).
trainable: `bool`. If True, this variable weights will be trained.
collections: `str`. A collection to add the new variable to (optional).
device: `str`. Device ID to store the variable. Default: '/cpu:0'.
restore: `bool`. Restore or not this variable when loading a
pre-trained model (Only compatible with tflearn pre-built
training functions).
Returns:
A Variable.
"""
if isinstance(initializer, str):
initializer = tflearn.initializations.get(initializer)()
# Remove shape param if initializer is a Tensor
if not callable(initializer) and isinstance(initializer, tf.Tensor):
shape = None
if isinstance(regularizer, str):
regularizer = tflearn.losses.get(regularizer)
with tf.device(device):
try:
var = tf.get_variable(name, shape=shape, dtype=dtype,
initializer=initializer,
regularizer=regularizer,
trainable=trainable,
collections=collections)
# Fix for old TF versions
except Exception as e:
var = tf.get_variable(name, shape=shape, dtype=dtype,
initializer=initializer,
trainable=trainable,
collections=collections)
if regularizer is not None:
tflearn.add_weights_regularizer(var, regularizer)
if not restore:
tf.add_to_collection(tf.GraphKeys.EXCL_RESTORE_VARS, var)
return var
def create_critic_network(self):
inputs = tflearn.input_data(shape=[None, self.s_dim])
action = tflearn.input_data(shape=[None, self.a_dim])
net = tflearn.fully_connected(inputs, 400, weights_init='xavier', bias_init='zeros')
tflearn.add_weights_regularizer(net, 'L2', weight_decay=0.001)
net = tflearn.layers.normalization.batch_normalization(net)
net = tflearn.activations.relu(net)
# Add the action tensor in the 2nd hidden layer
# Use two temp layers to get the corresponding weights and biases
t1 = tflearn.fully_connected(net, 300, weights_init='xavier', bias_init='zeros')
t2 = tflearn.fully_connected(action, 300, weights_init='xavier', bias_init='zeros')
net = tflearn.activation(tf.matmul(net, t1.W) + tf.matmul(action, t2.W) + t2.b, activation='relu')
# linear layer connected to 1 output representing Q(s,a)
# Weights are init to Uniform[-3e-3, 3e-3]
w_init = tflearn.initializations.uniform(minval=-0.003, maxval=0.003)
#out = tflearn.fully_connected(net, self.a_dim, weights_init=w_init)
out = tflearn.fully_connected(net, 1, weights_init=w_init)
return inputs, action, out
from tflearn.helpers.regularizer import add_weights_regularizer from tensorflow.contrib.slim import dataset from tensorflow.contrib.slim import dataset tflearn.input_data() tflearn.variable() tflearn.conv_2d() tflearn.single_unit() tflearn.lstm() tflearn.embedding() tflearn.batch_normalization() tflearn.merge() tflearn.regression() tflearn.tanh() tflearn.softmax_categorical_crossentropy() tflearn.SGD() tflearn.initializations.uniform() tflearn.losses.L1() tflearn.add_weights_regularizer() tflearn.metrics.Accuracy() tflearn.summaries() tflearn.ImagePreprocessing() tflearn.ImageAugmentation() tflearn.init_graph()
