本文整理汇总了Python中tensorflow.contrib.slim.conv2d_transpose方法的典型用法代码示例。如果您正苦于以下问题:Python slim.conv2d_transpose方法的具体用法?Python slim.conv2d_transpose怎么用?Python slim.conv2d_transpose使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类tensorflow.contrib.slim
的用法示例。
在下文中一共展示了slim.conv2d_transpose方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _extra_conv_arg_scope
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def _extra_conv_arg_scope(weight_decay=0.00001, activation_fn=None, normalizer_fn=None):
with slim.arg_scope(
[slim.conv2d, slim.conv2d_transpose],
padding='SAME',
weights_regularizer=slim.l2_regularizer(weight_decay),
weights_initializer=tf.truncated_normal_initializer(stddev=0.001),
activation_fn=activation_fn,
normalizer_fn=normalizer_fn,) as arg_sc:
with slim.arg_scope(
[slim.fully_connected],
weights_regularizer=slim.l2_regularizer(weight_decay),
weights_initializer=tf.truncated_normal_initializer(stddev=0.001),
activation_fn=activation_fn,
normalizer_fn=normalizer_fn) as arg_sc:
return arg_sc
示例2: upsample
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def upsample(x,scale=2,features=64,activation=tf.nn.relu):
assert scale in [2,3,4]
x = slim.conv2d(x,features,[3,3],activation_fn=activation)
if scale == 2:
ps_features = 3*(scale**2)
x = slim.conv2d(x,ps_features,[3,3],activation_fn=activation)
#x = slim.conv2d_transpose(x,ps_features,6,stride=1,activation_fn=activation)
x = PS(x,2,color=True)
elif scale == 3:
ps_features =3*(scale**2)
x = slim.conv2d(x,ps_features,[3,3],activation_fn=activation)
#x = slim.conv2d_transpose(x,ps_features,9,stride=1,activation_fn=activation)
x = PS(x,3,color=True)
elif scale == 4:
ps_features = 3*(2**2)
for i in range(2):
x = slim.conv2d(x,ps_features,[3,3],activation_fn=activation)
#x = slim.conv2d_transpose(x,ps_features,6,stride=1,activation_fn=activation)
x = PS(x,2,color=True)
return x
示例3: build_model
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def build_model(self):
with slim.arg_scope([slim.conv2d, slim.conv2d_transpose], activation_fn=tf.nn.elu):
with tf.variable_scope('model', reuse=self.reuse_variables):
self.left_pyramid = self.scale_pyramid(self.left, 4)
if self.mode == 'train':
self.right_pyramid = self.scale_pyramid(self.right, 4)
self.model_input = self.left
#build model
if self.params.encoder == 'vgg':
self.build_vgg(self.model_input)
elif self.params.encoder == 'resnet50':
self.build_resnet50()
else:
return None
示例4: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(self, inputs, reuse=False):
# inputs: (batch, 1, 1, 128)
with tf.variable_scope('generator', reuse=reuse):
with slim.arg_scope([slim.conv2d_transpose], padding='SAME', activation_fn=None,
stride=2, weights_initializer=tf.contrib.layers.xavier_initializer()):
with slim.arg_scope([slim.batch_norm], decay=0.95, center=True, scale=True,
activation_fn=tf.nn.relu, is_training=(self.mode=='train')):
net = slim.conv2d_transpose(inputs, 512, [4, 4], padding='VALID', scope='conv_transpose1') # (batch_size, 4, 4, 512)
net = slim.batch_norm(net, scope='bn1')
net = slim.conv2d_transpose(net, 256, [3, 3], scope='conv_transpose2') # (batch_size, 8, 8, 256)
net = slim.batch_norm(net, scope='bn2')
net = slim.conv2d_transpose(net, 128, [3, 3], scope='conv_transpose3') # (batch_size, 16, 16, 128)
net = slim.batch_norm(net, scope='bn3')
net = slim.conv2d_transpose(net, 1, [3, 3], activation_fn=tf.nn.tanh, scope='conv_transpose4') # (batch_size, 32, 32, 1)
return net
示例5: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
bn_kwargs = {
'is_training': is_training, 'updates_collections': None
}
# Network
net = slim.fully_connected(z, output_size//16 * output_size//16 * 8*f_dim,
activation_fn=None, normalizer_fn=None
)
net = tf.reshape(net, [-1, output_size//16, output_size//16, 8*f_dim])
net = lrelu(slim.batch_norm(net, **bn_kwargs))
conv2d_trp_argscope = slim.arg_scope([slim.conv2d_transpose],
kernel_size=[5,5], stride=[2,2], activation_fn=lrelu, normalizer_params=bn_kwargs,
)
with conv2d_trp_argscope:
net = slim.conv2d_transpose(net, 4*f_dim, normalizer_fn=slim.batch_norm)
net = slim.conv2d_transpose(net, 2*f_dim, normalizer_fn=slim.batch_norm)
net = slim.conv2d_transpose(net, f_dim, normalizer_fn=slim.batch_norm)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例6: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
# Network
net = slim.fully_connected(z, output_size//8 * output_size//8 * f_dim, activation_fn=None)
net = tf.reshape(net, [-1, output_size//8, output_size//8, f_dim])
net = lrelu(net)
conv2d_trp_argscope = slim.arg_scope(
[slim.conv2d_transpose], kernel_size=[5, 5], stride=[2, 2], activation_fn=lrelu
)
with conv2d_trp_argscope:
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例7: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
# Network
net = slim.fully_connected(z, output_size//16 * output_size//16 * f_dim, activation_fn=None)
net = tf.reshape(net, [-1, output_size//16, output_size//16, f_dim])
net = lrelu(net)
conv2d_trp_argscope = slim.arg_scope(
[slim.conv2d_transpose], kernel_size=[5, 5], stride=[2, 2], activation_fn=lrelu
)
with conv2d_trp_argscope:
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例8: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
# Network
net = slim.fully_connected(z, output_size//8 * output_size//8 * 4*f_dim, activation_fn=tf.nn.relu)
net = tf.reshape(net, [-1, output_size//8, output_size//8, 4*f_dim])
conv2d_trp_argscope = slim.arg_scope([slim.conv2d_transpose],
kernel_size=[5,5], stride=[2,2], activation_fn=tf.nn.relu,
)
with conv2d_trp_argscope:
net = slim.conv2d_transpose(net, 2*f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例9: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
# Network
net = slim.fully_connected(z, 512, activation_fn=lrelu)
net = slim.fully_connected(net, output_size//16 * output_size//16 * f_dim, activation_fn=lrelu)
net = tf.reshape(net, [-1, output_size//16, output_size//16, f_dim])
conv2dtrp_argscope = slim.arg_scope(
[slim.conv2d_transpose], kernel_size=[5, 5], stride=[2, 2], activation_fn=lrelu)
with conv2dtrp_argscope:
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, f_dim)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例10: generator
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def generator(z, f_dim, output_size, c_dim, is_training=True):
bn_kwargs = {
'is_training': is_training, 'updates_collections': None
}
# Network
net = slim.fully_connected(z, output_size//8 * output_size//8 * 4*f_dim,
activation_fn=tf.nn.relu, normalizer_fn=slim.batch_norm, normalizer_params=bn_kwargs
)
net = tf.reshape(net, [-1, output_size//8, output_size//8, 4*f_dim])
conv2d_trp_argscope = slim.arg_scope([slim.conv2d_transpose],
kernel_size=[5,5], stride=[2,2], activation_fn=tf.nn.relu, normalizer_params=bn_kwargs,
)
with conv2d_trp_argscope:
net = slim.conv2d_transpose(net, 2*f_dim, normalizer_fn=slim.batch_norm)
net = slim.conv2d_transpose(net, f_dim, normalizer_fn=slim.batch_norm)
net = slim.conv2d_transpose(net, c_dim, activation_fn=None)
out = tf.nn.tanh(net)
return out
示例11: readout_general
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def readout_general(multi_scale_belief, num_neurons, strides, layers_per_block,
kernel_size, batch_norm_is_training_op, wt_decay):
multi_scale_belief = tf.stop_gradient(multi_scale_belief)
with tf.variable_scope('readout_maps_deconv'):
x, outs = deconv(multi_scale_belief, batch_norm_is_training_op,
wt_decay=wt_decay, neurons=num_neurons, strides=strides,
layers_per_block=layers_per_block, kernel_size=kernel_size,
conv_fn=slim.conv2d_transpose, offset=0,
name='readout_maps_deconv')
probs = tf.sigmoid(x)
return x, probs
示例12: _building_ctx
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def _building_ctx(self, scope_name, reuse):
with tf.variable_scope(scope_name, reuse=reuse):
with slim.arg_scope([slim.conv2d, slim.conv2d_transpose, residual_block],
weights_regularizer=slim.l2_regularizer(self.config.regularization_factor),
data_format='NCHW'):
yield
示例13: _batch_norm_scope
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def _batch_norm_scope(self, is_training):
batch_norm_params = self._batch_norm_params(is_training)
with slim.arg_scope([slim.conv2d, slim.conv2d_transpose],
normalizer_fn=slim.batch_norm,
normalizer_params=batch_norm_params):
with slim.arg_scope([slim.batch_norm], **batch_norm_params):
yield
示例14: _decode
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def _decode(self, q, is_training):
with self._batch_norm_scope(is_training):
n = arch_param_n
fa = 3
fb = 5
net = slim.conv2d_transpose(q, n, [fa, fa], stride=2, scope='from_bn')
residual_input_0 = net
for b in range(self.config.arch_param_B):
residual_input_b = net
with tf.variable_scope('res_block_dec_{}'.format(b)):
net = residual_block(net, n, num_conv2d=2, kernel_size=[3, 3], scope='dec_{}_1'.format(b))
net = residual_block(net, n, num_conv2d=2, kernel_size=[3, 3], scope='dec_{}_2'.format(b))
net = residual_block(net, n, num_conv2d=2, kernel_size=[3, 3], scope='dec_{}_3'.format(b))
net = net + residual_input_b
net = residual_block(net, n, num_conv2d=2, kernel_size=[3, 3], scope='dec_after_res',
activation_fn=None)
net = net + residual_input_0
net = slim.conv2d_transpose(net, n // 2, [fb, fb], stride=2, scope='h12')
net = slim.conv2d_transpose(net, 3, [fb, fb], stride=2, scope='h13', activation_fn=None)
net = self._denormalize(net)
net = self._clip_to_image_range(net)
return net
# ------------------------------------------------------------------------------
示例15: deconv_bn_relu
# 需要导入模块: from tensorflow.contrib import slim [as 别名]
# 或者: from tensorflow.contrib.slim import conv2d_transpose [as 别名]
def deconv_bn_relu(inputs, filters, kernel_size=4, strides=2):
"""Paramaters for Deconvolution were chosen to avoid artifacts, following
link https://distill.pub/2016/deconv-checkerboard/
"""
with tf.variable_scope(None, 'deconv_bn_relu'):
output=slim.conv2d_transpose(inputs,filters,kernel_size=kernel_size,stride=strides,biases_initializer=None,activation_fn=None)
output = slim.batch_norm(output, activation_fn=tf.nn.relu, fused=False)
return output