Python tflearn.conv_2d() Examples
The following are 30
code examples of tflearn.conv_2d().
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
tflearn
, or try the search function
.
.
Example #1
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 8 votes |
|
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
net = input_data(shape=[None, width, height, 3], name='input')
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 32, 32)
net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 64, 32)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, output, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
loss='categorical_crossentropy')
model = tflearn.DNN(net,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #2
| Source File: cnn.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def CNN_Core(x, reuse=False):
with tf.variable_scope('cnn_core', reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL // 2, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
# network = tflearn.fully_connected(
# network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #3
| Source File: cnn.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def vgg16(input, num_class):
network = tflearn.conv_2d(
input, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
x = tflearn.fully_connected(
network, num_class, activation='sigmoid', scope='fc8')
return x
Example #4
| Source File: atari_1step_qlearning.py From FRU with MIT License | 6 votes |
|
def build_dqn(num_actions, action_repeat):
"""
Building a DQN.
"""
inputs = tf.placeholder(tf.float32, [None, action_repeat, 84, 84])
# Inputs shape: [batch, channel, height, width] need to be changed into
# shape [batch, height, width, channel]
net = tf.transpose(inputs, [0, 2, 3, 1])
net = tflearn.conv_2d(net, 32, 8, strides=4, activation='relu')
net = tflearn.conv_2d(net, 64, 4, strides=2, activation='relu')
net = tflearn.fully_connected(net, 256, activation='relu')
q_values = tflearn.fully_connected(net, num_actions)
return inputs, q_values
# =============================
# ATARI Environment Wrapper
# =============================
Example #5
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 6 votes |
|
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
net = input_data(shape=[None, width, height, 3], name='input')
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 32, 32)
net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 64, 32)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, output, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
loss='categorical_crossentropy')
model = tflearn.DNN(net,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #6
| Source File: a3c.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def create_critic_network(self):
with tf.variable_scope('critic'):
inputs = tflearn.input_data(
shape=[None, self.s_dim[0], self.s_dim[1]])
_input = tf.expand_dims(inputs, -1)
merge_net = tflearn.conv_2d(
_input, FEATURE_NUM, KERNEL, activation='relu')
merge_net = tflearn.conv_2d(
merge_net, FEATURE_NUM, KERNEL, activation='relu')
avg_net = tflearn.global_avg_pool(merge_net)
# dense_net_0 = tflearn.fully_connected(
# merge_net, 64, activation='relu')
#dense_net_0 = tflearn.dropout(dense_net_0, 0.8)
out = tflearn.fully_connected(avg_net, 1, activation='linear')
return inputs, out
Example #7
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 6 votes |
|
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
net = input_data(shape=[None, width, height, 3], name='input')
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 32, 32)
net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 64, 32)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, output, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
loss='categorical_crossentropy')
model = tflearn.DNN(net,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #8
| Source File: cnn.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def vgg16(input, num_class):
network = tflearn.conv_2d(
input, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
x = tflearn.fully_connected(
network, num_class, activation='sigmoid', scope='fc8')
return x
Example #9
| Source File: cnn.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def CNN_Core(x, reuse=False):
with tf.variable_scope('cnn_core', reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL // 2, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
# network = tflearn.fully_connected(
# network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #10
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 6 votes |
|
def resnext(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
net = input_data(shape=[None, width, height, 3], name='input')
net = tflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = tflearn.layers.conv.resnext_block(net, n, 16, 32)
net = tflearn.resnext_block(net, 1, 32, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 32, 32)
net = tflearn.resnext_block(net, 1, 64, 32, downsample=True)
net = tflearn.resnext_block(net, n-1, 64, 32)
net = tflearn.batch_normalization(net)
net = tflearn.activation(net, 'relu')
net = tflearn.global_avg_pool(net)
# Regression
net = tflearn.fully_connected(net, output, activation='softmax')
opt = tflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = tflearn.regression(net, optimizer=opt,
loss='categorical_crossentropy')
model = tflearn.DNN(net,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #11
| Source File: a3c.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def create_critic_network(self):
with tf.variable_scope('critic'):
inputs = tflearn.input_data(
shape=[None, self.s_dim[0], self.s_dim[1]])
_input = tf.expand_dims(inputs, -1)
merge_net = tflearn.conv_2d(
_input, FEATURE_NUM, KERNEL, activation='relu')
merge_net = tflearn.conv_2d(
merge_net, FEATURE_NUM, KERNEL, activation='relu')
avg_net = tflearn.global_avg_pool(merge_net)
# dense_net_0 = tflearn.fully_connected(
# merge_net, 64, activation='relu')
#dense_net_0 = tflearn.dropout(dense_net_0, 0.8)
out = tflearn.fully_connected(avg_net, 1, activation='linear')
return inputs, out
Example #12
| Source File: a3c.py From QARC with BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def create_actor_network(self):
with tf.variable_scope('actor'):
inputs = tflearn.input_data(
shape=[None, self.s_dim[0], self.s_dim[1]])
_input = tf.expand_dims(inputs, -1)
merge_net = tflearn.conv_2d(
_input, FEATURE_NUM, KERNEL, activation='relu')
merge_net = tflearn.conv_2d(
merge_net, FEATURE_NUM, KERNEL, activation='relu')
avg_net = tflearn.global_avg_pool(merge_net)
out = tflearn.fully_connected(
avg_net, self.a_dim, activation='softmax')
return inputs, out
Example #13
| Source File: vgg16.py From models with MIT License | 5 votes |
|
def vgg16(placeholderX=None):
x = tflearn.input_data(shape=[None, 224, 224, 3], name='input',
placeholder=placeholderX)
x = tflearn.conv_2d(x, 64, 3, activation='relu', scope='conv1_1')
x = tflearn.conv_2d(x, 64, 3, activation='relu', scope='conv1_2')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool1')
x = tflearn.conv_2d(x, 128, 3, activation='relu', scope='conv2_1')
x = tflearn.conv_2d(x, 128, 3, activation='relu', scope='conv2_2')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool2')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_1')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_2')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool3')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_1')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_2')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool4')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_1')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_2')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool5')
x = tflearn.fully_connected(x, 4096, activation='relu', scope='fc6')
x = tflearn.dropout(x, 0.5, name='dropout1')
x = tflearn.fully_connected(x, 4096, activation='relu', scope='fc7')
x = tflearn.dropout(x, 0.5, name='dropout2')
x = tflearn.fully_connected(x, 1000, activation='softmax', scope='fc8')
return x
Example #14
| Source File: vqn.py From QARC with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def CNN_Core(x,reuse=False):
with tf.variable_scope('cnn_core',reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2",weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2",weight_decay=0.0001)
network = tflearn.max_pool_2d(network, 2)
#network = tflearn.fully_connected(
# network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #15
| Source File: vqpn.py From QARC with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def CNN_Core(x,reuse=False):
with tf.variable_scope('cnn_core',reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 3, activation='relu', regularizer="L2",weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 3)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2",weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.fully_connected(
network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #16
| Source File: convert_VQPN.py From QARC with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def CNN_Core(self, x, reuse=False):
with tf.variable_scope('cnn_core', reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 3)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.fully_connected(
network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #17
| Source File: vqn-cnn.py From QARC with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def CNN_Core(x, reuse=False):
with tf.variable_scope('cnn_core', reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 3)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.fully_connected(
network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #18
| Source File: innovation_env.py From QARC with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def CNN_Core(self, x, reuse=False):
with tf.variable_scope('cnn_core', reuse=reuse):
network = tflearn.conv_2d(
x, KERNEL, 5, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 3)
network = tflearn.conv_2d(
network, KERNEL, 3, activation='relu', regularizer="L2", weight_decay=0.0001)
network = tflearn.avg_pool_2d(network, 2)
network = tflearn.fully_connected(
network, DENSE_SIZE, activation='relu')
split_flat = tflearn.flatten(network)
return split_flat
Example #19
| Source File: johnson.py From TensorFlowBook with Apache License 2.0 | 5 votes |
|
def generator(input_image):
relu = tf.nn.relu
conv2d = tflearn.conv_2d
def batch_norm(x):
mean, var = tf.nn.moments(x, axes=[1, 2, 3])
return tf.nn.batch_normalization(x, mean, var, 0, 1, 1e-5)
def deconv2d(x, n_filter, ksize, strides=1):
_, h, w, _ = x.get_shape().as_list()
output_shape = [strides * h, strides * w]
return tflearn.conv_2d_transpose(x, n_filter, ksize, output_shape,
strides)
def res_block(x):
net = relu(batch_norm(conv2d(x, 128, 3)))
net = batch_norm(conv2d(net, 128, 3))
return x + net
net = relu(batch_norm(conv2d(input_image, 32, 9)))
net = relu(batch_norm(conv2d(net, 64, 4, strides=2)))
net = relu(batch_norm(conv2d(net, 128, 4, strides=2)))
for i in range(5):
net = res_block(net)
net = relu(batch_norm(deconv2d(net, 64, 4, strides=2)))
net = relu(batch_norm(deconv2d(net, 32, 4, strides=2)))
net = deconv2d(net, 3, 9)
return net
Example #20
| Source File: manager.py From Fruit-API with GNU General Public License v3.0 | 5 votes |
|
def create_conv_layer(self, input_data, num_of_filters, filter_size, strides,
activation_fn='relu', padding='valid', permutation=None, scope=None):
if permutation is not None:
input_data = tf.transpose(input_data, permutation)
conv = tflearn.conv_2d(input_data, nb_filter=num_of_filters, filter_size=filter_size, strides=strides,
activation=activation_fn, padding=padding, scope=scope)
self.hiddens.append(conv)
self.num_of_hidden_layers += 1
return conv
Example #21
| Source File: vgg_network_finetuning.py From FRU with MIT License | 5 votes |
|
def vgg16(input, num_class):
x = tflearn.conv_2d(input, 64, 3, activation='relu', scope='conv1_1')
x = tflearn.conv_2d(x, 64, 3, activation='relu', scope='conv1_2')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool1')
x = tflearn.conv_2d(x, 128, 3, activation='relu', scope='conv2_1')
x = tflearn.conv_2d(x, 128, 3, activation='relu', scope='conv2_2')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool2')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_1')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_2')
x = tflearn.conv_2d(x, 256, 3, activation='relu', scope='conv3_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool3')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_1')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_2')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv4_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool4')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_1')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_2')
x = tflearn.conv_2d(x, 512, 3, activation='relu', scope='conv5_3')
x = tflearn.max_pool_2d(x, 2, strides=2, name='maxpool5')
x = tflearn.fully_connected(x, 4096, activation='relu', scope='fc6')
x = tflearn.dropout(x, 0.5, name='dropout1')
x = tflearn.fully_connected(x, 4096, activation='relu', scope='fc7')
x = tflearn.dropout(x, 0.5, name='dropout2')
x = tflearn.fully_connected(x, num_class, activation='softmax', scope='fc8',
restore=False)
return x
Example #22
| Source File: dcgan.py From FRU with MIT License | 5 votes |
|
def generator(x, reuse=False):
with tf.variable_scope('Generator', reuse=reuse):
x = tflearn.fully_connected(x, n_units=7 * 7 * 128)
x = tflearn.batch_normalization(x)
x = tf.nn.tanh(x)
x = tf.reshape(x, shape=[-1, 7, 7, 128])
x = tflearn.upsample_2d(x, 2)
x = tflearn.conv_2d(x, 64, 5, activation='tanh')
x = tflearn.upsample_2d(x, 2)
x = tflearn.conv_2d(x, 1, 5, activation='sigmoid')
return x
# Discriminator
Example #23
| Source File: dcgan.py From FRU with MIT License | 5 votes |
|
def discriminator(x, reuse=False):
with tf.variable_scope('Discriminator', reuse=reuse):
x = tflearn.conv_2d(x, 64, 5, activation='tanh')
x = tflearn.avg_pool_2d(x, 2)
x = tflearn.conv_2d(x, 128, 5, activation='tanh')
x = tflearn.avg_pool_2d(x, 2)
x = tflearn.fully_connected(x, 1024, activation='tanh')
x = tflearn.fully_connected(x, 2)
x = tf.nn.softmax(x)
return x
# Input Data
Example #24
| Source File: test_layers.py From FRU with MIT License | 5 votes |
|
def test_conv_layers(self):
X = [[0., 0., 0., 0.], [1., 1., 1., 1.], [0., 0., 1., 0.], [1., 1., 1., 0.]]
Y = [[1., 0.], [0., 1.], [1., 0.], [0., 1.]]
with tf.Graph().as_default():
g = tflearn.input_data(shape=[None, 4])
g = tflearn.reshape(g, new_shape=[-1, 2, 2, 1])
g = tflearn.conv_2d(g, 4, 2, activation='relu')
g = tflearn.max_pool_2d(g, 2)
g = tflearn.fully_connected(g, 2, activation='softmax')
g = tflearn.regression(g, optimizer='sgd', learning_rate=1.)
m = tflearn.DNN(g)
m.fit(X, Y, n_epoch=100, snapshot_epoch=False)
# TODO: Fix test
#self.assertGreater(m.predict([[1., 0., 0., 0.]])[0][0], 0.5)
# Bulk Tests
with tf.Graph().as_default():
g = tflearn.input_data(shape=[None, 4])
g = tflearn.reshape(g, new_shape=[-1, 2, 2, 1])
g = tflearn.conv_2d(g, 4, 2)
g = tflearn.conv_2d(g, 4, 1)
g = tflearn.conv_2d_transpose(g, 4, 2, [2, 2])
g = tflearn.max_pool_2d(g, 2)
Example #25
| Source File: texture_net.py From TensorFlowBook with Apache License 2.0 | 5 votes |
|
def generator(input_image):
conv2d = tflearn.conv_2d
batch_norm = tflearn.batch_normalization
relu = tf.nn.relu
ratios = [16, 8, 4, 2, 1]
n_filter = 8
net = []
for i in range(len(ratios)):
net.append(tflearn.max_pool_2d(input_image, ratios[i], ratios[i]))
# block_i_0, block_i_1, block_i_2
for block in range(3):
ksize = 1 if (block + 1) % 3 == 0 else 3
net[i] = relu(batch_norm(conv2d(net[i], n_filter, ksize)))
if i != 0:
# concat with net[i-1]
upnet = batch_norm(net[i - 1])
downnet = batch_norm(net[i])
net[i] = tf.concat(3, [upnet, downnet])
# block_i_3, block_i_4, block_i_5
for block in range(3, 6):
ksize = 1 if (block + 1) % 3 == 0 else 3
net[i] = conv2d(net[i], n_filter * (i + 1), ksize)
net[i] = relu(batch_norm(net[i]))
if i != len(ratios) - 1:
# upsample for concat
net[i] = tflearn.upsample_2d(net[i], 2)
nn = len(ratios) - 1
output = conv2d(net[nn], 3, 1)
return output
Example #26
| Source File: model.py From tensorflow2caffe with MIT License | 5 votes |
|
def vgg_net_19(width, height):
network = input_data(shape=[None, height, width, 3], name='input')
network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
network = dropout(network, keep_prob=0.5)
network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
network = dropout(network, keep_prob=0.5)
network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
opt = Momentum(learning_rate=0, momentum = 0.9)
network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
model = DNN(network, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
return model
#model of vgg-19 for testing of the activations
#rename the output you want to test, connect it to the next layer and change the output layer at the bottom (model = DNN(...))
#make sure to use the correct test function (depending if your output is a tensor or a vector)
Example #27
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 5 votes |
|
def sentnet_color_2d(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
network = input_data(shape=[None, width, height, 3], name='input')
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, output, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #28
| Source File: model.py From tensorflow2caffe with MIT License | 5 votes |
|
def vgg_net_19_activations(width, height):
network = input_data(shape=[None, height, width, 3], name='input')
network1 = conv_2d(network, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network2 = conv_2d(network1, 64, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network2, 2, strides=2)
network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 128, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 256, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = conv_2d(network, 512, 3, activation = 'relu', regularizer='L2', weight_decay=5e-4)
network = max_pool_2d(network, 2, strides=2)
network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
network = dropout(network, keep_prob=0.5)
network = fully_connected(network, 4096, activation='relu', weight_decay=5e-4)
network = dropout(network, keep_prob=0.5)
network = fully_connected(network, 1000, activation='softmax', weight_decay=5e-4)
opt = Momentum(learning_rate=0, momentum = 0.9)
network = regression(network, optimizer=opt, loss='categorical_crossentropy', name='targets')
model = DNN(network1, checkpoint_path='', max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='')
return model
Example #29
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 5 votes |
|
def sentnet_color_2d(width, height, frame_count, lr, output=9, model_name = 'sentnet_color.model'):
network = input_data(shape=[None, width, height, 3], name='input')
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, output, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network,
max_checkpoints=0, tensorboard_verbose=0, tensorboard_dir='log')
return model
Example #30
| Source File: models.py From pygta5 with GNU General Public License v3.0 | 5 votes |
|
def alexnet2(width, height, lr, output=3):
network = input_data(shape=[None, width, height, 1], name='input')
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.5)
network = fully_connected(network, output, activation='softmax')
network = regression(network, optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network, checkpoint_path='model_alexnet',
max_checkpoints=1, tensorboard_verbose=0, tensorboard_dir='log')
return model
