Python ops.fc() Examples
The following are 5
code examples of ops.fc().
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
ops
, or try the search function
.
.
Example #1
| Source File: inception_model.py From InceptionV3_TensorFlow with MIT License | 6 votes |
|
def inception_v3_parameters(weight_decay=0.00004, stddev=0.1,
batch_norm_decay=0.9997, batch_norm_epsilon=0.001):
"""Yields the scope with the default parameters for inception_v3.
Args:
weight_decay: the weight decay for weights variables.
stddev: standard deviation of the truncated guassian weight distribution.
batch_norm_decay: decay for the moving average of batch_norm momentums.
batch_norm_epsilon: small float added to variance to avoid dividing by zero.
Yields:
a arg_scope with the parameters needed for inception_v3.
"""
# Set weight_decay for weights in Conv and FC layers.
with scopes.arg_scope([ops.conv2d, ops.fc],
weight_decay=weight_decay):
# Set stddev, activation and parameters for batch_norm.
with scopes.arg_scope([ops.conv2d],
stddev=stddev,
activation=tf.nn.relu,
batch_norm_params={
'decay': batch_norm_decay,
'epsilon': batch_norm_epsilon}) as arg_scope:
yield arg_scope
Example #2
| Source File: generator.py From SSGAN-Tensorflow with MIT License | 5 votes |
|
def __call__(self, input):
if self._deconv_type == 'bilinear':
from ops import bilinear_deconv2d as deconv2d
elif self._deconv_type == 'nn':
from ops import nn_deconv2d as deconv2d
elif self._deconv_type == 'transpose':
from ops import deconv2d
else:
raise NotImplementedError
with tf.variable_scope(self.name, reuse=self._reuse):
if not self._reuse:
print('\033[93m'+self.name+'\033[0m')
_ = tf.reshape(input, [input.get_shape().as_list()[0], 1, 1, -1])
_ = fc(_, 1024, self._is_train, info=not self._reuse, norm='None', name='fc')
for i in range(int(np.ceil(np.log2(max(self._h, self._w))))):
_ = deconv2d(_, max(self._c, int(_.get_shape().as_list()[-1]/2)),
self._is_train, info=not self._reuse, norm=self._norm_type,
name='deconv{}'.format(i+1))
_ = deconv2d(_, self._c, self._is_train, k=1, s=1, info=not self._reuse,
activation_fn=tf.tanh, norm='None',
name='deconv{}'.format(i+2))
_ = tf.image.resize_bilinear(_, [self._h, self._w])
self._reuse = True
self.var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.name)
return _
Example #3
| Source File: kaggle_mnist_alexnet_model.py From tensorflow-alexnet with MIT License | 5 votes |
|
def inference(inputs, dropout_keep_prob, label_cnt):
# todo: change lrn parameters
# conv layer 1
with tf.name_scope('conv1layer'):
conv1 = op.conv(inputs, 7, 96, 3)
conv1 = op.lrn(conv1)
conv1 = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 1, 1, 1], padding='VALID')
# conv layer 2
with tf.name_scope('conv2layer'):
conv2 = op.conv(conv1, 5, 256, 1, 1.0)
conv2 = op.lrn(conv2)
conv2 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 1, 1, 1], padding='VALID')
# conv layer 3
with tf.name_scope('conv3layer'):
conv3 = op.conv(conv2, 3, 384, 1)
# conv layer 4
with tf.name_scope('conv4layer'):
conv4 = op.conv(conv3, 3, 384, 1, 1.0)
# conv layer 5
with tf.name_scope('conv5layer'):
conv5 = op.conv(conv4, 3, 256, 1, 1.0)
conv5 = tf.nn.max_pool(conv5, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='VALID')
# fc layer 1
with tf.name_scope('fc1layer'):
fc1 = op.fc(conv5, 4096, 1.0)
fc1 = tf.nn.dropout(fc1, dropout_keep_prob)
# fc layer 2
with tf.name_scope('fc2layer'):
fc2 = op.fc(fc1, 4096, 1.0)
fc2 = tf.nn.dropout(fc2, dropout_keep_prob)
# fc layer 3 - output
with tf.name_scope('fc3layer'):
return op.fc(fc2, label_cnt, 1.0, None)
Example #4
| Source File: generator.py From WGAN-GP-TensorFlow with MIT License | 5 votes |
|
def __call__(self, input):
if self._deconv_type == 'bilinear':
from ops import bilinear_deconv2d as deconv2d
elif self._deconv_type == 'nn':
from ops import nn_deconv2d as deconv2d
elif self._deconv_type == 'transpose':
from ops import deconv2d
else:
raise NotImplementedError
with tf.variable_scope(self.name, reuse=self._reuse):
if not self._reuse:
log.warn(self.name)
_ = fc(input, self.start_dim_x * self.start_dim_y * self.start_dim_ch,
self._is_train, info=not self._reuse, norm='none', name='fc')
_ = tf.reshape(_, [_.shape.as_list()[0], self.start_dim_y,
self.start_dim_x, self.start_dim_ch])
if not self._reuse:
log.info('reshape {} '.format(_.shape.as_list()))
num_deconv_layer = int(np.ceil(np.log2(
max(float(self._h/self.start_dim_y), float(self._w/self.start_dim_x)))))
for i in range(num_deconv_layer):
_ = deconv2d(_, max(self._c, int(_.get_shape().as_list()[-1]/2)),
self._is_train, info=not self._reuse, norm=self._norm_type,
name='deconv{}'.format(i+1))
if num_deconv_layer - i <= self._num_res_block:
_ = conv2d_res(
_, self._is_train, info=not self._reuse,
name='res_block{}'.format(self._num_res_block - num_deconv_layer + i + 1))
_ = deconv2d(_, self._c, self._is_train, k=1, s=1, info=not self._reuse,
activation_fn=tf.tanh, norm='none',
name='deconv{}'.format(i+2))
_ = tf.image.resize_bilinear(_, [self._h, self._w])
self._reuse = True
self.var_list = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, self.name)
return _
Example #5
| Source File: model_baseline.py From Relation-Network-Tensorflow with MIT License | 4 votes |
|
def build(self, is_train=True):
n = self.a_dim
conv_info = self.conv_info
# build loss and accuracy {{{
def build_loss(logits, labels):
# Cross-entropy loss
loss = tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=labels)
# Classification accuracy
correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(labels, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
return tf.reduce_mean(loss), accuracy
# }}}
# Classifier: takes images as input and outputs class label [B, m]
def C(img, q, scope='Classifier'):
with tf.variable_scope(scope) as scope:
log.warn(scope.name)
conv_1 = conv2d(img, conv_info[0], is_train, s_h=3, s_w=3, name='conv_1')
conv_2 = conv2d(conv_1, conv_info[1], is_train, s_h=3, s_w=3, name='conv_2')
conv_3 = conv2d(conv_2, conv_info[2], is_train, name='conv_3')
conv_4 = conv2d(conv_3, conv_info[3], is_train, name='conv_4')
conv_q = tf.concat([tf.reshape(conv_4, [self.batch_size, -1]), q], axis=1)
fc_1 = fc(conv_q, 256, name='fc_1')
fc_2 = fc(fc_1, 256, name='fc_2')
fc_2 = slim.dropout(fc_2, keep_prob=0.5, is_training=is_train, scope='fc_3/')
fc_3 = fc(fc_2, n, activation_fn=None, name='fc_3')
return fc_3
logits = C(self.img, self.q, scope='Classifier')
self.all_preds = tf.nn.softmax(logits)
self.loss, self.accuracy = build_loss(logits, self.a)
# Add summaries
def draw_iqa(img, q, target_a, pred_a):
fig, ax = tfplot.subplots(figsize=(6, 6))
ax.imshow(img)
ax.set_title(question2str(q))
ax.set_xlabel(answer2str(target_a)+answer2str(pred_a, 'Predicted'))
return fig
try:
tfplot.summary.plot_many('IQA/',
draw_iqa, [self.img, self.q, self.a, self.all_preds],
max_outputs=3,
collections=["plot_summaries"])
except:
pass
tf.summary.scalar("loss/accuracy", self.accuracy)
tf.summary.scalar("loss/cross_entropy", self.loss)
log.warn('Successfully loaded the model.')
