本文整理匯總了Python中prettytensor.defaults_scope方法的典型用法代碼示例。如果您正苦於以下問題：Python prettytensor.defaults_scope方法的具體用法？Python prettytensor.defaults_scope怎麽用？Python prettytensor.defaults_scope使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類prettytensor的用法示例。
在下文中一共展示了prettytensor.defaults_scope方法的15個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: build_model
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def build_model(sess, embedding_dim, batch_size):
model = CondGAN(
lr_imsize=cfg.TEST.LR_IMSIZE,
hr_lr_ratio=int(cfg.TEST.HR_IMSIZE/cfg.TEST.LR_IMSIZE))
embeddings = tf.placeholder(
tf.float32, [batch_size, embedding_dim],
name='conditional_embeddings')
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net"):
c = sample_encoded_context(embeddings, model)
z = tf.random_normal([batch_size, cfg.Z_DIM])
fake_images = model.get_generator(tf.concat(1, [c, z]))
with tf.variable_scope("hr_g_net"):
hr_c = sample_encoded_context(embeddings, model)
hr_fake_images = model.hr_get_generator(fake_images, hr_c)
ckt_path = cfg.TEST.PRETRAINED_MODEL
if ckt_path.find('.ckpt') != -1:
print("Reading model parameters from %s" % ckt_path)
saver = tf.train.Saver(tf.all_variables())
saver.restore(sess, ckt_path)
else:
print("Input a valid model path.")
return embeddings, fake_images, hr_fake_images 示例2: image2feature
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def image2feature(self, image_tensor):
if self.patch_feature_dim == 0:
return None
hgd = [
{"type": "conv2d", "depth": 32, "decoder_depth": 64},
{"type": "conv2d", "depth": 64, "decoder_depth": 64},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 40 x 40
{"type": "conv2d", "depth": 128},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 20x20
{"type": "conv2d", "depth": 256},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 10x10
{"type": "conv2d", "depth": 512},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
feature_map = hourglass(
image_tensor, hgd,
net_type=self.options["hourglass_type"] if "hourglass_type" in self.options else None
)
return feature_map 示例3: image2feature
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def image2feature(self, image_tensor):
if self.patch_feature_dim == 0:
return None
hgd = [
{"type": "conv2d", "depth": 32, "decoder_depth": 64},
{"type": "conv2d", "depth": 64, "decoder_depth": 64},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 40 x 40
{"type": "conv2d", "depth": 128},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 20x20
{"type": "conv2d", "depth": 256},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 10x10
{"type": "conv2d", "depth": 512},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
feature_map = hourglass(
image_tensor, hgd,
net_type=self.options["hourglass_type"] if "hourglass_type" in self.options else None
)
return feature_map 示例4: encoder
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def encoder(self, inputs, latent_size, activ=tf.nn.elu, phase=pt.Phase.train):
with pt.defaults_scope(activation_fn=activ,
batch_normalize=True,
learned_moments_update_rate=0.0003,
variance_epsilon=0.001,
scale_after_normalization=True,
phase=phase):
params = (pt.wrap(inputs).
reshape([-1, self.input_shape[0], self.input_shape[1], 1]).
conv2d(5, 32, stride=2).
conv2d(5, 64, stride=2).
conv2d(5, 128, edges='VALID').
#dropout(0.9).
flatten().
fully_connected(self.latent_size * 2, activation_fn=None)).tensor
mean = params[:, :self.latent_size]
stddev = params[:, self.latent_size:]
return [mean, stddev] 示例5: main_network
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def main_network(images, training):
x_pretty = pt.wrap(images)
if training:
phase = pt.Phase.train
else:
phase = pt.Phase.infer
with pt.defaults_scope(activation_fn=tf.nn.relu, phase=phase):
y_pred, loss = x_pretty.\
conv2d(kernel=5, depth=64, name="layer_conv1", batch_normalize=True).\
max_pool(kernel=2, stride=2).\
conv2d(kernel=5, depth=64, name="layer_conv2").\
max_pool(kernel=2, stride=2).\
flatten().\
fully_connected(size=256, name="layer_fc1").\
fully_connected(size=128, name="layer_fc2").\
softmax_classifier(num_classes, labels=y_true)
return y_pred, loss 示例6: init_opt
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def init_opt(self):
self.build_placeholder()
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope("g_net"):
# ####get output from G network################################
c, kl_loss = self.sample_encoded_context(self.embeddings)
z = tf.random_normal([self.batch_size, cfg.Z_DIM])
self.log_vars.append(("hist_c", c))
self.log_vars.append(("hist_z", z))
fake_images = self.model.get_generator(tf.concat(1, [c, z]))
# ####get discriminator_loss and generator_loss ###################
discriminator_loss, generator_loss =\
self.compute_losses(self.images,
self.wrong_images,
fake_images,
self.embeddings)
generator_loss += kl_loss
self.log_vars.append(("g_loss_kl_loss", kl_loss))
self.log_vars.append(("g_loss", generator_loss))
self.log_vars.append(("d_loss", discriminator_loss))
# #######Total loss for build optimizers###########################
self.prepare_trainer(generator_loss, discriminator_loss)
# #######define self.g_sum, self.d_sum,....########################
self.define_summaries()
with pt.defaults_scope(phase=pt.Phase.test):
with tf.variable_scope("g_net", reuse=True):
self.sampler()
self.visualization(cfg.TRAIN.NUM_COPY)
print("success") 示例7: _make_encoder_template
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def _make_encoder_template(self):
defaults_scope = {
'phase': pt.UnboundVariable('phase', default=pt.Phase.train),
'scale_after_normalization': True,
}
with pt.defaults_scope(**defaults_scope):
with tf.variable_scope("encoder"):
if self.network_type=="fully-connected":
z_dim = self.latent_dist.dist_flat_dim
self.encoder_template = (pt.template("x_in").
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(z_dim))
elif self.network_type=="convolutional":
z_dim = self.latent_dist.dist_flat_dim
self.encoder_template = (pt.template("x_in").
reshape([-1] + list(self.image_shape)).
custom_conv2d(64, k_h=4, k_w=4).
apply(tf.nn.elu).
custom_conv2d(128, k_h=4, k_w=4).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(1024).
batch_normalize().
apply(tf.nn.elu).
custom_fully_connected(z_dim)) 示例8: _make_decoder_template
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def _make_decoder_template(self):
defaults_scope = {
'phase': pt.UnboundVariable('phase', default=pt.Phase.train),
'scale_after_normalization': True,
}
image_size = self.image_shape[0]
with pt.defaults_scope(**defaults_scope):
with tf.variable_scope("decoder"):
if self.network_type=="fully-connected":
self.decoder_template = (pt.template("z_in").
custom_fully_connected(1000).
apply(tf.nn.relu).
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.relu).
custom_fully_connected(self.image_dim))
elif self.network_type=="convolutional":
self.decoder_template = \
(pt.template("z_in").
custom_fully_connected(1024).
batch_normalize().
apply(tf.nn.relu).
custom_fully_connected(image_size/4 * image_size/4 * 128).
batch_normalize().
apply(tf.nn.relu).
reshape([-1, image_size/4, image_size/4, 128]).
custom_deconv2d([0, image_size/2, image_size/2, 64],
k_h=4, k_w=4).
batch_normalize().
apply(tf.nn.relu).
custom_deconv2d([0] + list(self.image_shape),
k_h=4, k_w=4).
flatten()) 示例9: _make_discriminator_template
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def _make_discriminator_template(self):
defaults_scope = {
'phase': pt.UnboundVariable('phase', default=pt.Phase.train),
'scale_after_normalization': True,
}
with pt.defaults_scope(**defaults_scope):
with tf.variable_scope("discriminator"):
self.discriminator_template = (pt.template("z_in").
custom_fully_connected(1000).
apply(tf.nn.relu).
custom_fully_connected(1000).
batch_normalize().
apply(tf.nn.relu).
custom_fully_connected(1)) 示例10: multilayer_fully_connected
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def multilayer_fully_connected(images, labels):
images = pt.wrap(images)
with pt.defaults_scope(activation_fn=tf.nn.relu,l2loss=0.00001):
return (images.flatten().\
fully_connected(100).\
fully_connected(100).\
softmax_classifier(10, labels)) 開發者ID:PacktPublishing，項目名稱:Deep-Learning-with-TensorFlow-Second-Edition，代碼行數:9，代碼來源:pretty_tensor_digit.py
示例11: lenet5
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def lenet5(images, labels):
images = pt.wrap(images)
with pt.defaults_scope\
(activation_fn=tf.nn.relu, l2loss=0.00001):
return (images.conv2d(5, 20).\
max_pool(2, 2).\
conv2d(5, 50).\
max_pool(2, 2).\
flatten().\
fully_connected(500).\
softmax_classifier(10, labels)) 開發者ID:PacktPublishing，項目名稱:Deep-Learning-with-TensorFlow-Second-Edition，代碼行數:13，代碼來源:pretty_tensor_digit.py
示例12: build_model
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def build_model(self):
tf.reset_default_graph()
self._batch_shape = inp.get_batch_shape(FLAGS.batch_size, FLAGS.input_path)
self._current_step = tf.Variable(0, trainable=False, name='global_step')
self._step = tf.assign(self._current_step, self._current_step + 1)
with pt.defaults_scope(activation_fn=self._activation.func):
with pt.defaults_scope(phase=pt.Phase.train):
with tf.variable_scope(self.encoder_scope):
self._build_encoder()
with tf.variable_scope(self.decoder_scope):
self._build_decoder() 示例13: image2heatmap
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def image2heatmap(self, image_tensor):
hgd = [
{"type": "conv2d", "depth": 32, "decoder_depth": self.options["keypoint_num"] + 1,
"decoder_activation_fn": None},
# plus one for bg
{"type": "conv2d", "depth": 32},
{"type": "skip", "layer_num": 3, },
{"type": "pool", "pool": "max"},
{"type": "conv2d", "depth": 64},
{"type": "conv2d", "depth": 64},
{"type": "skip", "layer_num": 3, },
{"type": "pool", "pool": "max"},
{"type": "conv2d", "depth": 64},
{"type": "conv2d", "depth": 64},
{"type": "skip", "layer_num": 3, },
{"type": "pool", "pool": "max"},
{"type": "conv2d", "depth": 64},
{"type": "conv2d", "depth": 64},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
raw_heatmap = hourglass(
image_tensor, hgd,
net_type=self.options["hourglass_type"] if "hourglass_type" in self.options else None
)
# raw_heatmap = pt.wrap(raw_heatmap).pixel_bias(activation_fn=None).tensor
return raw_heatmap 示例14: image2heatmap
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def image2heatmap(self, image_tensor):
mid_tensor = (
pt.wrap(image_tensor).
conv2d(3, 32).
max_pool(2, 2)
).tensor
hgd = [
{"type": "conv2d", "depth": 64},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 32 x 32
{"type": "conv2d", "depth": 128},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 16 x 16
{"type": "conv2d", "depth": 256},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 8 x 8
{"type": "conv2d", "depth": 512},
{"type": "skip", "layer_num": 2},
{"type": "pool", "pool": "max", "kernel": 2, "stride": 2}, # 4 x 4
{"type": "conv2d", "depth": 512},
]
with pt.defaults_scope(**self.pt_defaults_scope_value()):
raw_heatmap_feat = hourglass(
mid_tensor, hgd,
net_type = self.options["hourglass_type"] if "hourglass_type" in self.options else None
)
return raw_heatmap_feat 示例15: bg_feature
# 需要導入模塊: import prettytensor [as 別名]
# 或者: from prettytensor import defaults_scope [as 別名]
def bg_feature(self, image_tensor):
with pt.defaults_scope(**self.pt_defaults_scope_value()):
return (
pt.wrap(image_tensor).
conv2d(3, 32).max_pool(2, 2). # 64
conv2d(3, 64).max_pool(2, 2). # 32
conv2d(3, 128).max_pool(2, 2). # 16
conv2d(3, 256).max_pool(2, 2). # 8
conv2d(3, 256).max_pool(2, 2). # 4
conv2d(3, 512).max_pool(2, 2). # 2
conv2d(3, 512)
)