Python tensorflow.contrib.slim.repeat() Examples
The following are 30
code examples of tensorflow.contrib.slim.repeat().
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
tensorflow.contrib.slim
, or try the search function
.
Example #1
Source File: vgg16.py From SSH-TensorFlow with MIT License | 6 votes |
def _image_to_head(self, is_training, reuse=None): with tf.variable_scope(self._scope, self._scope, reuse=reuse): net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') self.end_points['conv4_3'] = net net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') self.end_points['conv5_3'] = net self._act_summaries.append(net) self._layers['head'] = net
Example #2
Source File: vgg16.py From tf-faster-rcnn with MIT License | 6 votes |
def _image_to_head(self, is_training, reuse=None): with tf.variable_scope(self._scope, self._scope, reuse=reuse): net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') self._act_summaries.append(net) self._layers['head'] = net return net
Example #3
Source File: vgg16.py From tf_ctpn with MIT License | 6 votes |
def _image_to_head(self, is_training, reuse=None): with tf.variable_scope(self._scope, self._scope, reuse=reuse): net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=True, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=True, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=True, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=True, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=True, scope='conv5') self._act_summaries.append(net) self._layers['head'] = net return net
Example #4
Source File: vgg16.py From densecap-tensorflow with MIT License | 6 votes |
def _image_to_head(self, is_training, reuse=None): with tf.variable_scope(self._vgg_scope, self._vgg_scope, reuse=reuse): net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') self._act_summaries.append(net) self._layers['head'] = net return net
Example #5
Source File: vgg16.py From iter-reason with MIT License | 6 votes |
def _image_to_head(self, is_training, reuse=None): with tf.variable_scope(self._scope, self._scope, reuse=reuse): net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') self._act_summaries.append(net) self._layers['head'] = net return net
Example #6
Source File: tf_ops.py From long-term-video-prediction-without-supervision with Apache License 2.0 | 6 votes |
def get_repeat(end_points, prefix, final_endpoint): """Simulate `slim.repeat`, and add to endpoints dictionary.""" def repeat(net, repetitions, layer, *args, **kwargs): base_scope = kwargs['scope'] add_and_check_is_final = get_add_and_check_is_final(end_points, prefix, final_endpoint) with tf.variable_scope(base_scope, [net]): for i in xrange(repetitions): kwargs['scope'] = base_scope + '_' + str(i + 1) net = layer(net, *args, **kwargs) if add_and_check_is_final('%s_%i' % (base_scope, i), net): break return net return repeat
Example #7
Source File: benchmark_tensorflow.py From vgg-benchmarks with MIT License | 6 votes |
def vgg16(inputs, num_classes, batch_size): with slim.arg_scope([slim.conv2d, slim.fully_connected], activation_fn=tf.nn.relu, weights_initializer=tf.truncated_normal_initializer(0.0, 0.01)): net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], padding="SAME", scope='conv1') net = slim.max_pool2d(net, [2, 2], scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], padding="SAME", scope='conv2') net = slim.max_pool2d(net, [2, 2], scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], padding="SAME", scope='conv3') net = slim.max_pool2d(net, [2, 2], scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], padding="SAME", scope='conv4') net = slim.max_pool2d(net, [2, 2], scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], padding="SAME", scope='conv5') net = slim.max_pool2d(net, [2, 2], scope='pool5') net = tf.reshape(net, (batch_size, 7 * 7 * 512)) net = slim.fully_connected(net, 4096, scope='fc6') net = slim.dropout(net, 0.5, scope='dropout6') net = slim.fully_connected(net, 4096, scope='fc7') net = slim.dropout(net, 0.5, scope='dropout7') net = slim.fully_connected(net, 1000, activation_fn=None, scope='fc8') return net
Example #8
Source File: test_tf_converter.py From tf-coreml with Apache License 2.0 | 5 votes |
def test_slim_repeat(self): graph = tf.Graph() with graph.as_default() as g: inputs = tf.placeholder(tf.float32, shape=[None,16,16,3], name='test_slim_repeat/input') with slim.arg_scope([slim.conv2d], padding='SAME', weights_initializer=tf.truncated_normal_initializer(stddev=0.3), weights_regularizer=slim.l2_regularizer(0.0005)): net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') output_name = [net.op.name] self._test_tf_model(graph, {"test_slim_repeat/input:0":[1,16,16,3]}, output_name, delta=1e-2)
Example #9
Source File: dfc_vae_resnet.py From facenet_mtcnn_to_mobile with MIT License | 5 votes |
def decoder(self, latent_var, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('decoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = slim.fully_connected(latent_var, 4096, activation_fn=None, normalizer_fn=None, scope='Fc_1') net = tf.reshape(net, [-1,4,4,256], name='Reshape') net = tf.image.resize_nearest_neighbor(net, size=(8,8), name='Upsample_1') net = slim.conv2d(net, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = tf.image.resize_nearest_neighbor(net, size=(16,16), name='Upsample_2') net = slim.conv2d(net, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = tf.image.resize_nearest_neighbor(net, size=(32,32), name='Upsample_3') net = slim.conv2d(net, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = tf.image.resize_nearest_neighbor(net, size=(64,64), name='Upsample_4') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=None, scope='Conv2d_4c') return net
Example #10
Source File: layers.py From simulated-unsupervised-tensorflow with Apache License 2.0 | 5 votes |
def repeat(inputs, repetitions, layer, layer_dict={}, **kargv): outputs = slim.repeat(inputs, repetitions, layer, **kargv) _update_dict(layer_dict, kargv['scope'], outputs) return outputs
Example #11
Source File: KalmanVariationalAutoencoder.py From kvae with MIT License | 5 votes |
def encoder(self, x): """ Convolutional variational encoder to encode image into a low-dimensional latent code If config.conv == False it is a MLP VAE. If config.use_vae == False, it is a normal encoder :param x: sequence of images :return: a, a_mu, a_var """ with tf.variable_scope('vae/encoder'): if self.config.conv: x_flat_conv = tf.reshape(x, (-1, self.d1, self.d2, 1)) enc_hidden = slim.stack(x_flat_conv, slim.conv2d, self.num_filters, kernel_size=self.config.filter_size, stride=2, activation_fn=self.activation_fn, padding='SAME') enc_flat = slim.flatten(enc_hidden) self.enc_shape = enc_hidden.get_shape().as_list()[1:] else: x_flat = tf.reshape(x, (-1, self.d1 * self.d2)) enc_flat = slim.repeat(x_flat, self.config.num_layers, slim.fully_connected, self.config.vae_num_units, self.activation_fn) a_mu = slim.fully_connected(enc_flat, self.config.dim_a, activation_fn=None) if self.config.use_vae: a_var = slim.fully_connected(enc_flat, self.config.dim_a, activation_fn=tf.nn.sigmoid) a_var = self.config.noise_emission * a_var a = simple_sample(a_mu, a_var) else: a_var = tf.constant(1., dtype=tf.float32, shape=()) a = a_mu a_seq = tf.reshape(a, tf.stack((-1, self.ph_steps, self.config.dim_a))) return a_seq, a_mu, a_var
Example #12
Source File: dfc_vae_resnet.py From facenet-demo with MIT License | 5 votes |
def decoder(self, latent_var, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('decoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = slim.fully_connected(latent_var, 4096, activation_fn=None, normalizer_fn=None, scope='Fc_1') net = tf.reshape(net, [-1,4,4,256], name='Reshape') net = tf.image.resize_nearest_neighbor(net, size=(8,8), name='Upsample_1') net = slim.conv2d(net, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = tf.image.resize_nearest_neighbor(net, size=(16,16), name='Upsample_2') net = slim.conv2d(net, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = tf.image.resize_nearest_neighbor(net, size=(32,32), name='Upsample_3') net = slim.conv2d(net, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = tf.image.resize_nearest_neighbor(net, size=(64,64), name='Upsample_4') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=None, scope='Conv2d_4c') return net
Example #13
Source File: vgg16.py From Faster-RCNN-TensorFlow-Python3 with MIT License | 5 votes |
def build_head(self, is_training): # Main network # Layer 1 net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') # Layer 2 net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') # Layer 3 net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') # Layer 4 net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') # Layer 5 net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') # Append network to summaries self._act_summaries.append(net) # Append network as head layer self._layers['head'] = net return net
Example #14
Source File: dfc_vae_resnet.py From facenet-demo with MIT License | 5 votes |
def encoder(self, images, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('encoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = images net = slim.conv2d(net, 32, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = slim.conv2d(net, 64, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = slim.conv2d(net, 128, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = slim.conv2d(net, 256, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 256, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.flatten(net) fc1 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_1') fc2 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_2') return fc1, fc2
Example #15
Source File: ssd.py From SSD_tensorflow_VOC with Apache License 2.0 | 5 votes |
def get_model(self,inputs, weight_decay=0.0005,is_training=False): # End_points collect relevant activations for external use. arg_scope = self.__arg_scope(weight_decay=weight_decay) with slim.arg_scope(arg_scope): end_points = {} with tf.variable_scope('vgg_16', [inputs]): # Original VGG-16 blocks. net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') end_points['block1'] = net net = slim.max_pool2d(net, [2, 2], scope='pool1') # Block 2. net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2') end_points['block2'] = net net = slim.max_pool2d(net, [2, 2], scope='pool2') # Block 3. net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3') end_points['block3'] = net net = slim.max_pool2d(net, [2, 2], scope='pool3') # Block 4. net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4') end_points['block4'] = net net = slim.max_pool2d(net, [2, 2], scope='pool4') # Block 5. net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5') end_points['block5'] = net net = slim.max_pool2d(net, [3, 3], stride=1, scope='pool5') # Additional SSD blocks. keep_prob=0.8 with slim.arg_scope([slim.conv2d], activation_fn=None): with slim.arg_scope([slim.batch_norm], activation_fn=tf.nn.relu, is_training=is_training,updates_collections=None): with slim.arg_scope([slim.dropout], is_training=is_training,keep_prob=keep_prob): with tf.variable_scope(self.model_name): return self.__additional_ssd_block(end_points, net)
Example #16
Source File: layers.py From tf_autoencoder with Apache License 2.0 | 5 votes |
def conv_encoder(inputs, num_filters, scope=None): net = inputs with tf.variable_scope(scope, 'encoder', [inputs]): tf.assert_rank(inputs, 4) for layer_id, num_outputs in enumerate(num_filters): with tf.variable_scope('block{}'.format(layer_id)): net = slim.repeat(net, 2, conv2d_fixed_padding, num_outputs=num_outputs) net = tf.contrib.layers.max_pool2d(net) net = tf.identity(net, name='output') return net
Example #17
Source File: vgg16.py From GeetChinese_crack with MIT License | 5 votes |
def build_head(self, is_training): # Main network # Layer 1 net = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=False, scope='conv1') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool1') # Layer 2 net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], trainable=False, scope='conv2') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool2') # Layer 3 net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], trainable=is_training, scope='conv3') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool3') # Layer 4 net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv4') net = slim.max_pool2d(net, [2, 2], padding='SAME', scope='pool4') # Layer 5 net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') # Append network to summaries self._act_summaries.append(net) # Append network as head layer self._layers['head'] = net return net
Example #18
Source File: dfc_vae_resnet.py From facenet with MIT License | 5 votes |
def encoder(self, images, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('encoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = images net = slim.conv2d(net, 32, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = slim.conv2d(net, 64, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = slim.conv2d(net, 128, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = slim.conv2d(net, 256, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 256, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.flatten(net) fc1 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_1') fc2 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_2') return fc1, fc2
Example #19
Source File: dfc_vae_resnet.py From facenet with MIT License | 5 votes |
def decoder(self, latent_var, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('decoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = slim.fully_connected(latent_var, 4096, activation_fn=None, normalizer_fn=None, scope='Fc_1') net = tf.reshape(net, [-1,4,4,256], name='Reshape') net = tf.image.resize_nearest_neighbor(net, size=(8,8), name='Upsample_1') net = slim.conv2d(net, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = tf.image.resize_nearest_neighbor(net, size=(16,16), name='Upsample_2') net = slim.conv2d(net, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = tf.image.resize_nearest_neighbor(net, size=(32,32), name='Upsample_3') net = slim.conv2d(net, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = tf.image.resize_nearest_neighbor(net, size=(64,64), name='Upsample_4') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=None, scope='Conv2d_4c') return net
Example #20
Source File: dfc_vae_resnet.py From facenet_mtcnn_to_mobile with MIT License | 5 votes |
def encoder(self, images, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('encoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = images net = slim.conv2d(net, 32, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = slim.conv2d(net, 64, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = slim.conv2d(net, 128, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = slim.conv2d(net, 256, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 256, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.flatten(net) fc1 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_1') fc2 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_2') return fc1, fc2
Example #21
Source File: vgg16.py From MSDS-RCNN with MIT License | 5 votes |
def _image_to_rpn_single(self, is_training, initializer, reuse=False): """ Single modality input """ with tf.variable_scope(self._scope, self._scope, reuse=reuse): net_rgb = slim.repeat(self._image, 2, slim.conv2d, 64, [3, 3], trainable=is_training and 1 > cfg.VGG16.FIXED_BLOCKS, scope='conv1') self._tensor4debug['net_rgb1'] = net_rgb net_rgb = slim.max_pool2d(net_rgb, [2, 2], padding='SAME', scope='pool1') net_rgb = slim.repeat(net_rgb, 2, slim.conv2d, 128, [3, 3], trainable=is_training and 2 > cfg.VGG16.FIXED_BLOCKS, scope='conv2') net_rgb = slim.max_pool2d(net_rgb, [2, 2], padding='SAME', scope='pool2') net_rgb = slim.repeat(net_rgb, 3, slim.conv2d, 256, [3, 3], trainable=is_training and 3 > cfg.VGG16.FIXED_BLOCKS, scope='conv3') net_rgb = slim.max_pool2d(net_rgb, [2, 2], padding='SAME', scope='pool3') net_rgb = slim.repeat(net_rgb, 3, slim.conv2d, 512, [3, 3], trainable=is_training and 4 > cfg.VGG16.FIXED_BLOCKS, scope='conv4') if not cfg.REMOVE_POOLING: net_rgb = slim.max_pool2d(net_rgb, [2, 2], padding='SAME', scope='pool4') net_rgb = slim.repeat(net_rgb, 3, slim.conv2d, 512, [3, 3], trainable=is_training, scope='conv5') self._act_summaries.append(net_rgb) self._layers['head'] = net_rgb self._tensor4debug['net_rgb'] = net_rgb return net_rgb
Example #22
Source File: dfc_vae_resnet.py From tindetheus with MIT License | 5 votes |
def decoder(self, latent_var, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('decoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = slim.fully_connected(latent_var, 4096, activation_fn=None, normalizer_fn=None, scope='Fc_1') net = tf.reshape(net, [-1,4,4,256], name='Reshape') net = tf.image.resize_nearest_neighbor(net, size=(8,8), name='Upsample_1') net = slim.conv2d(net, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = tf.image.resize_nearest_neighbor(net, size=(16,16), name='Upsample_2') net = slim.conv2d(net, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = tf.image.resize_nearest_neighbor(net, size=(32,32), name='Upsample_3') net = slim.conv2d(net, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = tf.image.resize_nearest_neighbor(net, size=(64,64), name='Upsample_4') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=None, scope='Conv2d_4c') return net
Example #23
Source File: dfc_vae_resnet.py From tindetheus with MIT License | 5 votes |
def encoder(self, images, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('encoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = images net = slim.conv2d(net, 32, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = slim.conv2d(net, 64, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = slim.conv2d(net, 128, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = slim.conv2d(net, 256, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 256, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.flatten(net) fc1 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_1') fc2 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_2') return fc1, fc2
Example #24
Source File: train.py From DeepBlending with Apache License 2.0 | 5 votes |
def vgg_16(inputs, scope='vgg_16'): """Computes deep image features as the first two maxpooling layers of a VGG16 network""" with tf.variable_scope('vgg_16', 'vgg_16', [inputs], reuse=tf.AUTO_REUSE) as sc: end_points_collection = sc.original_name_scope + '_end_points' with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d], outputs_collections=end_points_collection): net_a = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') net_b = slim.max_pool2d(net_a, [2, 2], scope='pool1') net_c = slim.repeat(net_b, 2, slim.conv2d, 128, [3, 3], scope='conv2') return net_a, net_c
Example #25
Source File: utilities.py From bgsCNN with GNU General Public License v3.0 | 5 votes |
def vgg_16(inputs, variables_collections=None, scope='vgg_16', reuse=None): """ modification of vgg_16 in TF-slim see original code in https://github.com/tensorflow/models/blob/master/slim/nets/vgg.py """ with tf.variable_scope(scope, 'vgg_16', [inputs]) as sc: # Collect outputs for conv2d, fully_connected and max_pool2d. with slim.arg_scope([slim.conv2d, slim.fully_connected, slim.max_pool2d]): conv1 = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1', biases_initializer=None, variables_collections=variables_collections, reuse=reuse) pool1, argmax_1 = tf.nn.max_pool_with_argmax(conv1, [1,2,2,1], [1,2,2,1], padding='VALID', name='pool1') conv2 = slim.repeat(pool1, 2, slim.conv2d, 128, [3, 3], scope='conv2', biases_initializer=None, variables_collections=variables_collections, reuse=reuse) pool2, argmax_2 = tf.nn.max_pool_with_argmax(conv2, [1,2,2,1], [1,2,2,1], padding='VALID', name='pool2') conv3 = slim.repeat(pool2, 3, slim.conv2d, 256, [3, 3], scope='conv3', biases_initializer=None, variables_collections=variables_collections, reuse=reuse) pool3, argmax_3 = tf.nn.max_pool_with_argmax(conv3, [1,2,2,1], [1,2,2,1], padding='VALID', name='pool3') conv4 = slim.repeat(pool3, 3, slim.conv2d, 512, [3, 3], scope='conv4', biases_initializer=None, variables_collections=variables_collections, reuse=reuse) pool4, argmax_4 = tf.nn.max_pool_with_argmax(conv4, [1,2,2,1], [1,2,2,1], padding='VALID', name='pool4') conv5 = slim.repeat(pool4, 3, slim.conv2d, 512, [3, 3], scope='conv5', biases_initializer=None, variables_collections=variables_collections, reuse=reuse) pool5, argmax_5 = tf.nn.max_pool_with_argmax(conv5, [1,2,2,1], [1,2,2,1], padding='VALID', name='pool5') # return argmax argmax = (argmax_1, argmax_2, argmax_3, argmax_4, argmax_5) # return feature maps features = (conv1, conv2, conv3, conv4, conv5) return pool5, argmax, features
Example #26
Source File: archs.py From gaze_redirection with MIT License | 5 votes |
def vgg_16(inputs, scope='vgg_16', reuse=False): """ VGG-16. Parameters ---------- inputs: tensor. scope: name of scope. reuse: reuse the net if True. Returns ------- net: tensor, output tensor. end_points: dict, collection of layers. """ with tf.variable_scope(scope, 'vgg_16', [inputs], reuse=reuse) as sc: end_points_collection = sc.original_name_scope + '_end_points' # Collect outputs for conv2d, fully_connected and max_pool2d. with slim.arg_scope( [slim.conv2d, slim.fully_connected, slim.max_pool2d], outputs_collections=end_points_collection): net = slim.repeat(inputs, 2, slim.conv2d, 64, [3, 3], scope='conv1') net = slim.max_pool2d(net, [2, 2], scope='pool1') net = slim.repeat(net, 2, slim.conv2d, 128, [3, 3], scope='conv2') net = slim.max_pool2d(net, [2, 2], scope='pool2') net = slim.repeat(net, 3, slim.conv2d, 256, [3, 3], scope='conv3') net = slim.max_pool2d(net, [2, 2], scope='pool3') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv4') net = slim.max_pool2d(net, [2, 2], scope='pool4') net = slim.repeat(net, 3, slim.conv2d, 512, [3, 3], scope='conv5') net = slim.max_pool2d(net, [2, 2], scope='pool5') # Convert end_points_collection into a end_point dict. end_points = slim.utils.convert_collection_to_dict( end_points_collection) return net, end_points
Example #27
Source File: dfc_vae_resnet.py From TNT with GNU General Public License v3.0 | 5 votes |
def decoder(self, latent_var, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('decoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = slim.fully_connected(latent_var, 4096, activation_fn=None, normalizer_fn=None, scope='Fc_1') net = tf.reshape(net, [-1,4,4,256], name='Reshape') net = tf.image.resize_nearest_neighbor(net, size=(8,8), name='Upsample_1') net = slim.conv2d(net, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = tf.image.resize_nearest_neighbor(net, size=(16,16), name='Upsample_2') net = slim.conv2d(net, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = tf.image.resize_nearest_neighbor(net, size=(32,32), name='Upsample_3') net = slim.conv2d(net, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = tf.image.resize_nearest_neighbor(net, size=(64,64), name='Upsample_4') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 3, [3, 3], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.conv2d(net, 3, [3, 3], 1, activation_fn=None, scope='Conv2d_4c') return net
Example #28
Source File: dfc_vae_resnet.py From TNT with GNU General Public License v3.0 | 5 votes |
def encoder(self, images, is_training): activation_fn = leaky_relu # tf.nn.relu weight_decay = 0.0 with tf.variable_scope('encoder'): with slim.arg_scope([slim.batch_norm], is_training=is_training): with slim.arg_scope([slim.conv2d, slim.fully_connected], weights_initializer=tf.truncated_normal_initializer(stddev=0.1), weights_regularizer=slim.l2_regularizer(weight_decay), normalizer_fn=slim.batch_norm, normalizer_params=self.batch_norm_params): net = images net = slim.conv2d(net, 32, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_1a') net = slim.repeat(net, 3, conv2d_block, 0.1, 32, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_1b') net = slim.conv2d(net, 64, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_2a') net = slim.repeat(net, 3, conv2d_block, 0.1, 64, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_2b') net = slim.conv2d(net, 128, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_3a') net = slim.repeat(net, 3, conv2d_block, 0.1, 128, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_3b') net = slim.conv2d(net, 256, [4, 4], 2, activation_fn=activation_fn, scope='Conv2d_4a') net = slim.repeat(net, 3, conv2d_block, 0.1, 256, [4, 4], 1, activation_fn=activation_fn, scope='Conv2d_4b') net = slim.flatten(net) fc1 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_1') fc2 = slim.fully_connected(net, self.latent_variable_dim, activation_fn=None, normalizer_fn=None, scope='Fc_2') return fc1, fc2
Example #29
Source File: KalmanVariationalAutoencoder.py From kvae with MIT License | 4 votes |
def decoder(self, a_seq): """ Convolutional variational decoder to decode latent code to image reconstruction If config.conv == False it is a MLP VAE. If config.use_vae == False it is a normal decoder :param a_seq: latent code :return: x_hat, x_mu, x_var """ # Create decoder if self.config.out_distr == 'bernoulli': activation_x_mu = tf.nn.sigmoid else: activation_x_mu = None with tf.variable_scope('vae/decoder'): a = tf.reshape(a_seq, (-1, self.config.dim_a)) if self.config.conv: dec_upscale = slim.fully_connected(a, int(np.prod(self.enc_shape)), activation_fn=None) dec_upscale = tf.reshape(dec_upscale, [-1] + self.enc_shape) dec_hidden = dec_upscale for filters in reversed(self.num_filters): dec_hidden = slim.conv2d(dec_hidden, filters * 4, self.config.filter_size, activation_fn=self.activation_fn) dec_hidden = subpixel_reshape(dec_hidden, 2) x_mu = slim.conv2d(dec_hidden, 1, 1, stride=1, activation_fn=activation_x_mu) x_var = tf.constant(self.config.noise_pixel_var, dtype=tf.float32, shape=()) else: dec_hidden = slim.repeat(a, self.config.num_layers, slim.fully_connected, self.config.vae_num_units, self.activation_fn) x_mu = slim.fully_connected(dec_hidden, self.d1 * self.d2, activation_fn=activation_x_mu) x_mu = tf.reshape(x_mu, (-1, self.d1, self.d2, 1)) # x_var is not used for bernoulli outputs. Here we fix the output variance of the Gaussian, # we could also learn it globally for each pixel (as we did in the pendulum experiment) or through a # neural network. x_var = tf.constant(self.config.noise_pixel_var, dtype=tf.float32, shape=()) if self.config.out_distr == 'bernoulli': # For bernoulli we show the probabilities x_hat = x_mu else: x_hat = simple_sample(x_mu, x_var) return tf.reshape(x_hat, tf.stack((-1, self.ph_steps, self.d1, self.d2))), x_mu, x_var
Example #30
Source File: KalmanVariationalAutoencoder.py From kvae with MIT License | 4 votes |
def alpha(self, inputs, state=None, u=None, buffer=None, reuse=None, init_buffer=False, name='alpha'): """The dynamics parameter network alpha for mixing transitions in a state space model. This function is quite general and supports different architectures (NN, RNN, FIFO queue, learning the inputs) Args: inputs: tensor to condition mixing vector on state: previous state if using RNN network to model alpha u: pass-through variable if u is given (learn_u=False) buffer: buffer for the FIFO network (used for fifo_size>1) reuse: `True` or `None`; if `True`, we go into reuse mode for this scope as well as all sub-scopes; if `None`, we just inherit the parent scope reuse. init_buffer: initialize buffer for a_t name: name of the scope Returns: alpha: mixing vector of dimension (batch size, K) state: new state u: either inferred u from model or pass-through buffer: FIFO buffer """ # Increase the number of hidden units if we also learn u (learn_u=True) num_units = self.config.alpha_units * 2 if self.config.learn_u else self.config.alpha_units # Overwrite input buffer if init_buffer: buffer = tf.zeros((tf.shape(inputs)[0], self.config.dim_a, self.config.fifo_size), dtype=tf.float32) # If K == 1, return inputs if self.config.K == 1: return tf.ones([self.config.batch_size, self.config.K]), state, u, buffer with tf.variable_scope(name, reuse=reuse): if self.config.alpha_rnn: rnn_cell = BasicLSTMCell(num_units, reuse=reuse) output, state = rnn_cell(inputs, state) else: # Shift buffer buffer = tf.concat([buffer[:, :, 1:], tf.expand_dims(inputs, 2)], 2) output = slim.repeat( tf.reshape(buffer, (tf.shape(inputs)[0], self.config.dim_a * self.config.fifo_size)), self.config.alpha_layers, slim.fully_connected, num_units, get_activation_fn(self.config.alpha_activation), scope='hidden') # Get Alpha as the first part of the output alpha = slim.fully_connected(output[:, :self.config.alpha_units], self.config.K, activation_fn=tf.nn.softmax, scope='alpha_var') if self.config.learn_u: # Get U as the second half of the output u = slim.fully_connected(output[:, self.config.alpha_units:], self.config.dim_u, activation_fn=None, scope='u_var') return alpha, state, u, buffer