def load_mnist_convnet_5(path):
## your code here
input = tflearn.input_data(shape=[None, 28, 28, 1])
cov1 = tflearn.conv_2d(input, nb_filter=120, filter_size=10, activation='sigmoid', name='conv_layer_1')
max_pool1 = tflearn.max_pool_2d(cov1, 2, name='pool1')
lrn = tflearn.local_response_normalization(max_pool1)
cov2 = tflearn.conv_2d(lrn, nb_filter=80, filter_size=10, activation='sigmoid', name='conv_layer_2')
max_pool2 = tflearn.max_pool_2d(cov2, 2, name='pool2')
lrn2 = tflearn.local_response_normalization(max_pool2)
cov3 = tflearn.conv_2d(lrn2, nb_filter=40, filter_size=10, activation='sigmoid', name='conv_layer_3')
max_pool3 = tflearn.max_pool_2d(cov3, 2, name='pool3')
fc1 = tflearn.fully_connected(max_pool3, 30, activation='sigmoid')
fc2 = tflearn.fully_connected(fc1, 10, activation='softmax')
model = tflearn.DNN(fc2)
def conv_net(input_shape, **kwargs):
net = input_data(shape=input_shape)
net = conv_2d(net, 32, 3, activation='relu',
regularizer="L2") # filter_size=32, nb_filter=3
net = max_pool_2d(net, 2)
net = local_response_normalization(net)
net = conv_2d(net, 64, 3, activation='relu', regularizer="L2")
net = max_pool_2d(net, 2)
net = local_response_normalization(net)
net = fully_connected(net, 128, activation='tanh')
net = dropout(net, 0.8)
net = fully_connected(net, 256, activation='tanh')
net = dropout(net, 0.8)
net = fully_connected(net, 10, activation='softmax')
return net
def LoadModel(self):
self.window_height = 16
self.window_width = 8
self.threshold = 0.03
self.ground_height = 2
symbol_count = 13
network = input_data(
shape=[None, self.window_height, self.window_width, symbol_count])
network = conv_2d(network, 16, 2, activation='leaky_relu')
network = max_pool_2d(network, 2)
network = local_response_normalization(network)
network = fully_connected(network,
self.window_height * symbol_count,
activation='relu')
network = tf.reshape(network, [-1, self.window_height, symbol_count])
network = regression(network,
optimizer='adagrad',
learning_rate=0.005,
loss='mean_square',
name='target',
batch_size=64)
self.model = tflearn.DNN(network)
self.model.load('./CNNmodel/model.tfl')
def conv(X_train, y_train, X_test, y_test):
# reshape data
X_train = X_train.reshape([-1, 28, 28, 1])
X_test = X_test.reshape([-1, 28, 28, 1])
# build network
network = tflearn.input_data(shape=[None, 28, 28, 1], name='input')
network = tflearn.conv_2d(network,
32,
3,
activation='relu',
regularizer="L2")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.conv_2d(network,
64,
3,
activation='relu',
regularizer="L2")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.fully_connected(network, 128, activation='tanh')
network = tflearn.dropout(network, 0.8)
network = tflearn.fully_connected(network, 256, activation='tanh')
network = tflearn.dropout(network, 0.8)
network = tflearn.fully_connected(network, 10, activation='softmax')
network = tflearn.regression(network,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target')
# train conv net
model = tflearn.DNN(network, tensorboard_verbose=0)
model.fit({'input': X_train}, {'target': y_train},
n_epoch=20,
validation_set=({
'input': X_test
}, {
'target': y_test
}),
snapshot_step=100,
show_metric=True)
def create_actor_network(self):
inputs = tflearn.input_data(shape=[None, 75, 100, 1], name='input')
net = tflearn.conv_2d(inputs, 32, 3, activation='relu', regularizer="L2")
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.conv_2d(net, 64, 3, activation='relu', regularizer="L2")
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.conv_2d(net, 128, 2, activation='relu', regularizer="L2")
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
# Final layer weights are init to Uniform[-3e-3, 3e-3]
w_init = tflearn.initializations.uniform(minval=-0.01, maxval=0.01)
#w_init = tflearn.initializations.uniform(minval=-0.003, maxval=0.003)
out = tflearn.fully_connected(
net, self.a_dim, activation='tanh', weights_init=w_init)
# Scale output to -action_bound to action_bound
scaled_out = tf.multiply(out, self.action_bound)
return inputs, out, scaled_out
def load_mnist_convnet_3(path):
## your code here
input = tflearn.input_data(shape=[None, 28, 28, 1])
cov1 = tflearn.conv_2d(input, nb_filter=32, filter_size=5, activation='relu', name='conv_layer_1')
max_pool1 = tflearn.max_pool_2d(cov1, 2, name='pool1')
lrn = tflearn.local_response_normalization(max_pool1)
cov2 = tflearn.conv_2d(lrn, nb_filter=32, filter_size=5, activation='relu', name='conv_layer_2')
max_pool2 = tflearn.max_pool_2d(cov2, 2, name='pool2')
fc1 = tflearn.fully_connected(max_pool2, 100, activation='relu')
fc2 = tflearn.fully_connected(fc1, 10, activation='softmax')
model = tflearn.DNN(fc2)
def build_tflearn_convnet_1():
# your code here
input = tflearn.input_data(shape=[None, 28, 28, 1])
cov1 = tflearn.conv_2d(input, nb_filter=64, filter_size=5, activation='sigmoid', name='conv_layer_1')
max_pool1 = tflearn.max_pool_2d(cov1, 2, name='pool1')
lrn = tflearn.local_response_normalization(max_pool1)
cov2 = tflearn.conv_2d(lrn, nb_filter=32, filter_size=5, activation='sigmoid', name='conv_layer_2')
max_pool2 = tflearn.max_pool_2d(cov2, 2, name='pool2')
fc1 = tflearn.fully_connected(max_pool2, 100, activation='sigmoid')
fc2 = tflearn.fully_connected(fc1, 10, activation='softmax')
reg = tflearn.regression(fc2, optimizer='sgd', loss='categorical_crossentropy', learning_rate=0.1)
return tflearn.DNN(reg)
def conv_neural_network_model(self):
conv1_filters = 10
conv2_filters = 6
pool2_flat_dense_size = 100
network = tflearn.input_data(shape=[None, self.n_frames * self.n_mfcc],
name='input')
network = tflearn.reshape(
network, new_shape=[-1, self.n_frames, self.n_mfcc, 1])
network = tflearn.conv_2d(network,
conv1_filters,
5,
activation='relu',
regularizer="L2")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.conv_2d(network,
conv2_filters,
5,
activation='relu',
regularizer="L2")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.fully_connected(network,
pool2_flat_dense_size,
activation='tanh',
regularizer="L2")
#network = tflearn.dropout(network, 0.1)
network = tflearn.fully_connected(network,
self.n_classes,
activation='softmax')
network = tflearn.regression(network,
optimizer='adam',
learning_rate=self.learning_rate,
loss='categorical_crossentropy',
name='target')
self.model = tflearn.DNN(network, tensorboard_verbose=0)
return self.model
def convnet():
model = tf.input_data(shape=[None, 5, 19, 5], name='input')
model = tf.conv_2d(model, 32, 3, activation='relu', regularizer="L2")
model = tf.max_pool_2d(model, 2)
model = tf.local_response_normalization(model)
model = tf.conv_2d(model, 64, 3, activation='relu', regularizer="L2")
model = tf.max_pool_2d(model, 2)
model = tf.local_response_normalization(model)
model = tf.fully_connected(model, 128, activation='tanh')
model = tf.dropout(model, 0.8)
model = tf.fully_connected(model, 256, activation='tanh')
model = tf.dropout(model, 0.8)
model = tf.fully_connected(model, 11, activation='sigmoid')
model = tf.regression(model,
optimizer='adam',
learning_rate=0.01,
loss='categorical_crossentropy',
name='target')
model = tf.DNN(model, tensorboard_verbose=0)
return model
def build_cnn_bird(dim_s, dim_a):
inputs = tf.placeholder(tf.float32, shape=[None] + dim_s)
net = tf.image.resize_images(inputs, size=(80, 80))
net = tflearn.conv_2d(net, 32, 8, strides=4, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.conv_2d(net, 64, 4, strides=2, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.fully_connected(net, 512, activation='relu')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 512, activation='relu')
net = tflearn.dropout(net, 0.8)
q_values = tflearn.fully_connected(net, dim_a)
return inputs, q_values
def vgg16basic(input_data, num_class):
conv1 = tflearn.conv_2d(input_data, 96, 11, strides=4, activation='relu')
pool1 = tflearn.max_pool_2d(conv1, 3, strides=2)
network = tflearn.local_response_normalization(pool1)
conv2 = tflearn.conv_2d(network, 256, 5, activation='relu')
pool2 = tflearn.max_pool_2d(conv2, 3, strides=2)
network = tflearn.local_response_normalization(pool2)
conv3 = tflearn.conv_2d(network, 384, 3, activation='relu')
conv4 = tflearn.conv_2d(conv3, 384, 3, activation='relu')
conv5 = tflearn.conv_2d(conv4, 256, 3, activation='relu')
pool3 = tflearn.max_pool_2d(conv5, 3, strides=2)
network = tflearn.local_response_normalization(pool3)
fc1 = tflearn.fully_connected(network, 4096, activation='tanh')
dropout1 = tflearn.dropout(fc1, 0.5)
fc2 = tflearn.fully_connected(dropout1, 2048, activation='tanh')
dropout2 = tflearn.dropout(fc2, 0.5)
fc3 = tflearn.fully_connected(dropout2, 2, activation='softmax')
return fc3
def create_actor_network(self):
inputs = tflearn.input_data(shape=[None, self.s_dim])
net = tflearn.fully_connected(inputs, 400, activation=lambda x: tflearn.activations.leaky_relu(x, alpha=0.2))
#net = tflearn.layers.normalization.batch_normalization(net)
net = tflearn.local_response_normalization(net)
#net = tflearn.fully_connected(net, 600,activation='relu', regularizer='L1', decay=0.001)
net = tflearn.fully_connected(net, 600,activation=lambda x: tflearn.activations.leaky_relu(x, alpha=0.2), regularizer='L1', decay=0.001)
#net = tflearn.dropout(net, 0.7)
net = tflearn.fully_connected(net, 300,activation=lambda x: tflearn.activations.leaky_relu(x, alpha=0.2), regularizer='L1', decay=0.001)
#net = tflearn.local_response_normalization(net)
# Final layer weights are init to Uniform[-3e-3, 3e-3]
w_init = tflearn.initializations.uniform(minval=-0.003, maxval=0.003)
out = tflearn.fully_connected(
net, self.a_dim, activation='tanh', weights_init=w_init)
# Scale output to -action_bound to action_bound
scaled_out = tf.multiply(out, self.action_bound)
return inputs, out, scaled_out
# Load HDF5 dataset
import h5py
h5f = h5py.File('your file path.h5', 'r')
X = h5f['X']
Y = h5f['Y']
network = tflearn.input_data(shape=[None, 250, 250, 3])
network = tflearn.conv_2d(network,
64,
10,
4,
activation='relu',
regularizer="L1")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.conv_2d(network,
128,
11,
activation='relu',
regularizer="L1")
network = tflearn.max_pool_2d(network, 2)
network = tflearn.local_response_normalization(network)
network = tflearn.fully_connected(network, 128, activation='relu')
network = tflearn.dropout(network, 0.8)
network = tflearn.fully_connected(network, 32, activation='relu')
network = tflearn.fully_connected(network, 2, activation='sigmoid')
#top1 = tflearn.metrics.Top_k(k=1)
network = tflearn.regression(network,
# Using MNIST Dataset
import tflearn.datasets.mnist as mnist
mnist_data = mnist.read_data_sets(one_hot=True)
# User defined placeholders
with tf.Graph().as_default():
# Placeholders for data and labels
X = tf.placeholder(shape=(None, 784), dtype=tf.float32)
Y = tf.placeholder(shape=(None, 10), dtype=tf.float32)
net = tf.reshape(X, [-1, 28, 28, 1])
# Using TFLearn wrappers for network building
net = tflearn.conv_2d(net, 32, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.conv_2d(net, 64, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 128, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 10, activation='softmax')
# Defining other ops using Tensorflow
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss)
def inception(input_layer, num_class):
conv1_7_7 = tflearn.conv_2d(input_layer,
64,
7,
strides=2,
activation='relu',
name='conv1_7_7_s2')
pool1_3_3 = tflearn.max_pool_2d(conv1_7_7, 3, strides=2)
pool1_3_3 = tflearn.local_response_normalization(pool1_3_3)
conv2_3_3_reduce = tflearn.conv_2d(pool1_3_3,
64,
1,
activation='relu',
name='conv2_3_3_reduce')
conv2_3_3 = tflearn.conv_2d(conv2_3_3_reduce,
192,
3,
activation='relu',
name='conv2_3_3')
conv2_3_3 = tflearn.local_response_normalization(conv2_3_3)
pool2_3_3 = tflearn.max_pool_2d(conv2_3_3,
kernel_size=3,
strides=2,
name='pool2_3_3_s2')
inception_3a_1_1 = tflearn.conv_2d(pool2_3_3,
64,
1,
activation='relu',
name='inception_3a_1_1')
inception_3a_3_3_reduce = tflearn.conv_2d(pool2_3_3,
96,
1,
activation='relu',
name='inception_3a_3_3_reduce')
inception_3a_3_3 = tflearn.conv_2d(inception_3a_3_3_reduce,
128,
filter_size=3,
activation='relu',
name='inception_3a_3_3')
inception_3a_5_5_reduce = tflearn.conv_2d(pool2_3_3,
16,
filter_size=1,
activation='relu',
name='inception_3a_5_5_reduce')
inception_3a_5_5 = tflearn.conv_2d(inception_3a_5_5_reduce,
32,
filter_size=5,
activation='relu',
name='inception_3a_5_5')
inception_3a_pool = tflearn.max_pool_2d(
pool2_3_3,
kernel_size=3,
strides=1,
)
inception_3a_pool_1_1 = tflearn.conv_2d(inception_3a_pool,
32,
filter_size=1,
activation='relu',
name='inception_3a_pool_1_1')
# merge the inception_3a__
inception_3a_output = tflearn.merge([
inception_3a_1_1, inception_3a_3_3, inception_3a_5_5,
inception_3a_pool_1_1
],
mode='concat',
axis=3)
inception_3b_1_1 = tflearn.conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_1_1')
inception_3b_3_3_reduce = tflearn.conv_2d(inception_3a_output,
128,
filter_size=1,
activation='relu',
name='inception_3b_3_3_reduce')
inception_3b_3_3 = tflearn.conv_2d(inception_3b_3_3_reduce,
192,
filter_size=3,
activation='relu',
name='inception_3b_3_3')
inception_3b_5_5_reduce = tflearn.conv_2d(inception_3a_output,
32,
filter_size=1,
activation='relu',
name='inception_3b_5_5_reduce')
inception_3b_5_5 = tflearn.conv_2d(inception_3b_5_5_reduce,
96,
filter_size=5,
name='inception_3b_5_5')
inception_3b_pool = tflearn.max_pool_2d(inception_3a_output,
kernel_size=3,
strides=1,
name='inception_3b_pool')
inception_3b_pool_1_1 = tflearn.conv_2d(inception_3b_pool,
64,
filter_size=1,
activation='relu',
name='inception_3b_pool_1_1')
# merge the inception_3b_*
inception_3b_output = tflearn.merge([
inception_3b_1_1, inception_3b_3_3, inception_3b_5_5,
inception_3b_pool_1_1
],
mode='concat',
axis=3,
name='inception_3b_output')
pool3_3_3 = tflearn.max_pool_2d(inception_3b_output,
kernel_size=3,
strides=2,
name='pool3_3_3')
inception_4a_1_1 = tflearn.conv_2d(pool3_3_3,
192,
filter_size=1,
activation='relu',
name='inception_4a_1_1')
inception_4a_3_3_reduce = tflearn.conv_2d(pool3_3_3,
96,
filter_size=1,
activation='relu',
name='inception_4a_3_3_reduce')
inception_4a_3_3 = tflearn.conv_2d(inception_4a_3_3_reduce,
208,
filter_size=3,
activation='relu',
name='inception_4a_3_3')
inception_4a_5_5_reduce = tflearn.conv_2d(pool3_3_3,
16,
filter_size=1,
activation='relu',
name='inception_4a_5_5_reduce')
inception_4a_5_5 = tflearn.conv_2d(inception_4a_5_5_reduce,
48,
filter_size=5,
activation='relu',
name='inception_4a_5_5')
inception_4a_pool = tflearn.max_pool_2d(pool3_3_3,
kernel_size=3,
strides=1,
name='inception_4a_pool')
inception_4a_pool_1_1 = tflearn.conv_2d(inception_4a_pool,
64,
filter_size=1,
activation='relu',
name='inception_4a_pool_1_1')
inception_4a_output = tflearn.merge([
inception_4a_1_1, inception_4a_3_3, inception_4a_5_5,
inception_4a_pool_1_1
],
mode='concat',
axis=3,
name='inception_4a_output')
inception_4b_1_1 = tflearn.conv_2d(inception_4a_output,
160,
filter_size=1,
activation='relu',
name='inception_4a_1_1')
inception_4b_3_3_reduce = tflearn.conv_2d(inception_4a_output,
112,
filter_size=1,
activation='relu',
name='inception_4b_3_3_reduce')
inception_4b_3_3 = tflearn.conv_2d(inception_4b_3_3_reduce,
224,
filter_size=3,
activation='relu',
name='inception_4b_3_3')
inception_4b_5_5_reduce = tflearn.conv_2d(inception_4a_output,
24,
filter_size=1,
activation='relu',
name='inception_4b_5_5_reduce')
inception_4b_5_5 = tflearn.conv_2d(inception_4b_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4b_5_5')
inception_4b_pool = tflearn.max_pool_2d(inception_4a_output,
kernel_size=3,
strides=1,
name='inception_4b_pool')
inception_4b_pool_1_1 = tflearn.conv_2d(inception_4b_pool,
64,
filter_size=1,
activation='relu',
name='inception_4b_pool_1_1')
inception_4b_output = tflearn.merge([
inception_4b_1_1, inception_4b_3_3, inception_4b_5_5,
inception_4b_pool_1_1
],
mode='concat',
axis=3,
name='inception_4b_output')
inception_4c_1_1 = tflearn.conv_2d(inception_4b_output,
128,
filter_size=1,
activation='relu',
name='inception_4c_1_1')
inception_4c_3_3_reduce = tflearn.conv_2d(inception_4b_output,
128,
filter_size=1,
activation='relu',
name='inception_4c_3_3_reduce')
inception_4c_3_3 = tflearn.conv_2d(inception_4c_3_3_reduce,
256,
filter_size=3,
activation='relu',
name='inception_4c_3_3')
inception_4c_5_5_reduce = tflearn.conv_2d(inception_4b_output,
24,
filter_size=1,
activation='relu',
name='inception_4c_5_5_reduce')
inception_4c_5_5 = tflearn.conv_2d(inception_4c_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4c_5_5')
inception_4c_pool = tflearn.max_pool_2d(inception_4b_output,
kernel_size=3,
strides=1)
inception_4c_pool_1_1 = tflearn.conv_2d(inception_4c_pool,
64,
filter_size=1,
activation='relu',
name='inception_4c_pool_1_1')
inception_4c_output = tflearn.merge([
inception_4c_1_1, inception_4c_3_3, inception_4c_5_5,
inception_4c_pool_1_1
],
mode='concat',
axis=3,
name='inception_4c_output')
inception_4d_1_1 = tflearn.conv_2d(inception_4c_output,
112,
filter_size=1,
activation='relu',
name='inception_4d_1_1')
inception_4d_3_3_reduce = tflearn.conv_2d(inception_4c_output,
144,
filter_size=1,
activation='relu',
name='inception_4d_3_3_reduce')
inception_4d_3_3 = tflearn.conv_2d(inception_4d_3_3_reduce,
288,
filter_size=3,
activation='relu',
name='inception_4d_3_3')
inception_4d_5_5_reduce = tflearn.conv_2d(inception_4c_output,
32,
filter_size=1,
activation='relu',
name='inception_4d_5_5_reduce')
inception_4d_5_5 = tflearn.conv_2d(inception_4d_5_5_reduce,
64,
filter_size=5,
activation='relu',
name='inception_4d_5_5')
inception_4d_pool = tflearn.max_pool_2d(inception_4c_output,
kernel_size=3,
strides=1,
name='inception_4d_pool')
inception_4d_pool_1_1 = tflearn.conv_2d(inception_4d_pool,
64,
filter_size=1,
activation='relu',
name='inception_4d_pool_1_1')
inception_4d_output = tflearn.merge([
inception_4d_1_1, inception_4d_3_3, inception_4d_5_5,
inception_4d_pool_1_1
],
mode='concat',
axis=3,
name='inception_4d_output')
inception_4e_1_1 = tflearn.conv_2d(inception_4d_output,
256,
filter_size=1,
activation='relu',
name='inception_4e_1_1')
inception_4e_3_3_reduce = tflearn.conv_2d(inception_4d_output,
160,
filter_size=1,
activation='relu',
name='inception_4e_3_3_reduce')
inception_4e_3_3 = tflearn.conv_2d(inception_4e_3_3_reduce,
320,
filter_size=3,
activation='relu',
name='inception_4e_3_3')
inception_4e_5_5_reduce = tflearn.conv_2d(inception_4d_output,
32,
filter_size=1,
activation='relu',
name='inception_4e_5_5_reduce')
inception_4e_5_5 = tflearn.conv_2d(inception_4e_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_4e_5_5')
inception_4e_pool = tflearn.max_pool_2d(inception_4d_output,
kernel_size=3,
strides=1,
name='inception_4e_pool')
inception_4e_pool_1_1 = tflearn.conv_2d(inception_4e_pool,
128,
filter_size=1,
activation='relu',
name='inception_4e_pool_1_1')
inception_4e_output = tflearn.merge([
inception_4e_1_1, inception_4e_3_3, inception_4e_5_5,
inception_4e_pool_1_1
],
axis=3,
mode='concat')
pool4_3_3 = tflearn.max_pool_2d(inception_4e_output,
kernel_size=3,
strides=2,
name='pool_3_3')
inception_5a_1_1 = tflearn.conv_2d(pool4_3_3,
256,
filter_size=1,
activation='relu',
name='inception_5a_1_1')
inception_5a_3_3_reduce = tflearn.conv_2d(pool4_3_3,
160,
filter_size=1,
activation='relu',
name='inception_5a_3_3_reduce')
inception_5a_3_3 = tflearn.conv_2d(inception_5a_3_3_reduce,
320,
filter_size=3,
activation='relu',
name='inception_5a_3_3')
inception_5a_5_5_reduce = tflearn.conv_2d(pool4_3_3,
32,
filter_size=1,
activation='relu',
name='inception_5a_5_5_reduce')
inception_5a_5_5 = tflearn.conv_2d(inception_5a_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_5a_5_5')
inception_5a_pool = tflearn.max_pool_2d(pool4_3_3,
kernel_size=3,
strides=1,
name='inception_5a_pool')
inception_5a_pool_1_1 = tflearn.conv_2d(inception_5a_pool,
128,
filter_size=1,
activation='relu',
name='inception_5a_pool_1_1')
inception_5a_output_ = tflearn.merge([
inception_5a_1_1, inception_5a_3_3, inception_5a_5_5,
inception_5a_pool_1_1
],
axis=3,
mode='concat')
inception_5a_output = tflearn.dropout(inception_5a_output_, 0.45)
inception_5b_1_1 = tflearn.conv_2d(inception_5a_output,
384,
filter_size=1,
activation='relu',
name='inception_5b_1_1')
inception_5b_3_3_reduce = tflearn.conv_2d(inception_5a_output,
192,
filter_size=1,
activation='relu',
name='inception_5b_3_3_reduce')
inception_5b_3_3 = tflearn.conv_2d(inception_5b_3_3_reduce,
384,
filter_size=3,
activation='relu',
name='inception_5b_3_3')
inception_5b_5_5_reduce = tflearn.conv_2d(inception_5a_output,
48,
filter_size=1,
activation='relu',
name='inception_5b_5_5_reduce')
inception_5b_5_5 = tflearn.conv_2d(inception_5b_5_5_reduce,
128,
filter_size=5,
activation='relu',
name='inception_5b_5_5')
inception_5b_pool = tflearn.max_pool_2d(inception_5a_output,
kernel_size=3,
strides=1,
name='inception_5b_pool')
inception_5b_pool_1_1 = tflearn.conv_2d(inception_5b_pool,
128,
filter_size=1,
activation='relu',
name='inception_5b_pool_1_1')
inception_5b_output = tflearn.merge([
inception_5b_1_1, inception_5b_3_3, inception_5b_5_5,
inception_5b_pool_1_1
],
axis=3,
mode='concat')
pool5_7_7 = tflearn.avg_pool_2d(inception_5b_output,
kernel_size=7,
strides=1)
pool5_7_7 = tflearn.dropout(pool5_7_7, 0.65)
loss = tflearn.fully_connected(pool5_7_7, num_class, activation='softmax')
return loss
def run():
X = tf.placeholder(shape=(None, 784), dtype=tf.float32)
Y = tf.placeholder(shape=(None, 10), dtype=tf.float32)
net = tf.reshape(X, [-1, 28, 28, 1]) # batch, height, width, chnl
# 32 filters, each of size 3(x3)
net = tflearn.conv_2d(net, 32, 3, activation='relu')
# pool kernel size 2, stride size default kernel soze
net = tflearn.max_pool_2d(net, 2)
# for "encourage some kind of inhibition and boost the neurons with
# relatively larger activations"
net = tflearn.local_response_normalization(net)
# The dropout method is introduced to prevent overfitting. At each training stage, individual nodes are either "dropped out" of the net with probability {\displaystyle 1-p} 1-p or kept with probability {\displaystyle p} p, so that a reduced network is left
# keep_prob=0.8
net = tflearn.dropout(net, 0.8)
# 64 filters
net = tflearn.conv_2d(net, 64, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
# FC
net = tflearn.fully_connected(net, 128, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 10, activation='softmax')
# --------------------------------------
# really manual tf way
# # Defining other ops using Tensorflow
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
# optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
# optimizer_minop = optimizer.minimize(loss)
# # start
# init = tf.initialize_all_variables()
# with tf.Session() as sess:
# sess.run(init)
# batch_size = 128
# for epoch in range(2):
# avg_cost = 0.
# total_batch = int(mnist_data.train.num_examples/batch_size)
# for i in range(total_batch):
# batch_xs, batch_ys = mnist_data.train.next_batch(batch_size)
# sess.run(optimizer_minop, feed_dict={X: batch_xs, Y: batch_ys})
# cost = sess.run(loss, feed_dict={X: batch_xs, Y: batch_ys})
# avg_cost += cost/total_batch
# if i % 20 == 0:
# print("Epoch:", '%03d' % (epoch+1), "Step:", '%03d' % i,
# "Loss:", str(cost))
# --------------------------------------
# use trainer class
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
accuracy = tf.reduce_mean(tf.cast(
tf.equal(tf.argmax(net, 1), tf.argmax(Y, 1)),
tf.float32), name='acc')
trainop = tflearn.TrainOp(loss=loss, optimizer=optimizer,
metric=accuracy, batch_size=128)
trainer = tflearn.Trainer(train_ops=trainop, tensorboard_verbose=0)
trainer.fit({X: trainX, Y: trainY}, val_feed_dicts={
X: testX, Y: testY}, n_epoch=2, show_metric=True)
trainer.save('models/mnist_cnn.tfl')
def run():
X = tf.placeholder(shape=(None, 784), dtype=tf.float32)
Y = tf.placeholder(shape=(None, 10), dtype=tf.float32)
net = tf.reshape(X, [-1, 28, 28, 1]) # batch, height, width, chnl
# 32 filters, each of size 3(x3)
net = tflearn.conv_2d(net, 32, 3, activation='relu')
# pool kernel size 2, stride size default kernel soze
net = tflearn.max_pool_2d(net, 2)
# for "encourage some kind of inhibition and boost the neurons with
# relatively larger activations"
net = tflearn.local_response_normalization(net)
# The dropout method is introduced to prevent overfitting. At each training stage, individual nodes are either "dropped out" of the net with probability {\displaystyle 1-p} 1-p or kept with probability {\displaystyle p} p, so that a reduced network is left
# keep_prob=0.8
net = tflearn.dropout(net, 0.8)
# 64 filters
net = tflearn.conv_2d(net, 64, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
# FC
net = tflearn.fully_connected(net, 128, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 10, activation='softmax')
# --------------------------------------
# really manual tf way
# # Defining other ops using Tensorflow
# loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
# optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
# optimizer_minop = optimizer.minimize(loss)
# # start
# init = tf.initialize_all_variables()
# with tf.Session() as sess:
# sess.run(init)
# batch_size = 128
# for epoch in range(2):
# avg_cost = 0.
# total_batch = int(mnist_data.train.num_examples/batch_size)
# for i in range(total_batch):
# batch_xs, batch_ys = mnist_data.train.next_batch(batch_size)
# sess.run(optimizer_minop, feed_dict={X: batch_xs, Y: batch_ys})
# cost = sess.run(loss, feed_dict={X: batch_xs, Y: batch_ys})
# avg_cost += cost/total_batch
# if i % 20 == 0:
# print("Epoch:", '%03d' % (epoch+1), "Step:", '%03d' % i,
# "Loss:", str(cost))
# --------------------------------------
# use trainer class
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.01)
accuracy = tf.reduce_mean(tf.cast(
tf.equal(tf.argmax(net, 1), tf.argmax(Y, 1)), tf.float32),
name='acc')
trainop = tflearn.TrainOp(loss=loss,
optimizer=optimizer,
metric=accuracy,
batch_size=128)
trainer = tflearn.Trainer(train_ops=trainop, tensorboard_verbose=0)
trainer.fit({
X: trainX,
Y: trainY
},
val_feed_dicts={
X: testX,
Y: testY
},
n_epoch=2,
show_metric=True)
trainer.save('models/mnist_cnn.tfl')
reduce1 = tflearn.conv_2d(input, n1, 1, activation='relu')
reduce2 = tflearn.conv_2d(input, n2, filter_size=1, activation='relu')
pool = tflearn.max_pool_2d(input, kernel_size=3, strides=1)
conv1 = tflearn.conv_2d(input, n3, 1, activation='relu')
conv2 = tflearn.conv_2d(reduce1, n4, filter_size=3, activation='relu')
conv3 = tflearn.conv_2d(reduce2, n5, filter_size=5, activation='relu')
conv4 = tflearn.conv_2d(pool, n6, filter_size=1, activation='relu')
output = tflearn.merge([conv1, conv2, conv3, conv4], mode='concat', axis=3)
return output
input = tflearn.input_data(shape=[None, 227, 227, 3],
data_augmentation=img_aug)
conv1 = tflearn.conv_2d(input, 64, 7, strides=2, activation='relu')
m1 = tflearn.max_pool_2d(conv1, 3, strides=2)
l1 = tflearn.local_response_normalization(m1)
conv2 = tflearn.conv_2d(l1, 64, 1, activation='relu')
conv3 = tflearn.conv_2d(conv2, 192, 3, activation='relu')
l2 = tflearn.local_response_normalization(conv3)
m2 = tflearn.max_pool_2d(l2, kernel_size=3, strides=2)
i1 = inception(m2, 96, 16, 64, 128, 32, 32)
i2 = inception(i1, 128, 32, 128, 192, 96, 64)
m3 = tflearn.max_pool_2d(i2, kernel_size=3, strides=2)
i3 = inception(m3, 96, 16, 192, 208, 48, 64)
i4 = inception(i3, 112, 24, 160, 224, 64, 64)
i5 = inception(i4, 128, 24, 128, 256, 64, 64)
i6 = inception(i5, 144, 32, 112, 288, 64, 64)
i7 = inception(i6, 160, 32, 256, 320, 128, 128)
m4 = tflearn.max_pool_2d(i7, kernel_size=3, strides=2)
i8 = inception(m4, 160, 32, 256, 320, 128, 128)
i9 = inception(i8, 192, 48, 384, 384, 128, 128)
# Using MNIST Dataset
import tflearn.datasets.mnist as mnist
mnist_data = mnist.read_data_sets(one_hot=True)
# User defined placeholders
with tf.Graph().as_default():
# Placeholders for data and labels
X = tf.placeholder(shape=(None, 784), dtype=tf.float32)
Y = tf.placeholder(shape=(None, 10), dtype=tf.float32)
net = tf.reshape(X, [-1, 28, 28, 1])
# Using TFLearn wrappers for network building
net = tflearn.conv_2d(net, 32, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.conv_2d(net, 64, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 128, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 10, activation='linear')
# Defining other ops using Tensorflow
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(logits=net, labels=Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss)
def conv_encode(self, input_data):
conv1 = tflearn.conv_2d(input_data, 32, 5, activation='elu')
pool1 = tflearn.max_pool_2d(conv1, 2)
norm1 = tflearn.local_response_normalization(pool1)
return tf.reshape(norm1, [self.curr_batch_size, 6272])
def main():
'''
Establishes architecture for CNN-fully-connected-RNN neural net.
'''
# Create the input layer: None: batch size, 120: frames, 80: height, 80: width, 3: RGB
network = tflearn.input_data(shape=[None, 120, 80, 80, 3], name='input')
# Convolutional network
network = tflearn.conv_3d(
network, 32, (3, 3, 3), activation='relu'
) # 32 conv layers of 3x3x3 (3x3x3 convolves for each 3 frames, 3px height, and 3px width)
network = tflearn.max_pool_3d(
network, (1, 2, 2),
strides=(1, 2, 2)) # Pools results of the conv_3d layer
network = tflearn.conv_3d(network, 64, (3, 3, 3),
activation='relu') # 64 layers of 3x3x3
network = tflearn.max_pool_3d(network, (1, 2, 2), strides=(1, 2, 2))
network = tflearn.conv_3d(network, 128, (3, 3, 3),
activation='relu') # 128 layers of 3x3x3
network = tflearn.conv_3d(network, 128, (3, 3, 3),
activation='relu') # another one?
network = tflearn.max_pool_3d(network, (1, 2, 2), strides=(1, 2, 2))
network = tflearn.conv_3d(network, 256, (2, 2, 2),
activation='relu') # 256 layers of 2x2x2
network = tflearn.conv_3d(network, 256, (2, 2, 2), activation='relu')
network = tflearn.max_pool_3d(network, (1, 2, 2), strides=(1, 2, 2))
network = tflearn.conv_2d(network,
64,
4,
activation='relu',
regularizer="L2") # 64 layers of 4x4
network = tflearn.max_pool_2d(network, 2) # and then max pool
# Normalize activations of the previous layer at each batch.
network = tflearn.local_response_normalization(network)
# And now the fully-connected neural net (128 & 256 neurons + dropout)
network = tflearn.fully_connected(network, 128, activation='tanh')
network = tflearn.dropout(network, 0.8)
network = tflearn.fully_connected(network, 256, activation='tanh')
network = tflearn.dropout(network, 0.8)
network = tflearn.reshape(network, [-1, 1, 256]) # Why 256?
# LSTM layers
network = tflearn.lstm(network, 128, return_seq=True) # LSTM of 128 units
network = tflearn.lstm(network, 128)
network = tflearn.fully_connected(
network, 4, activation='softmax') # Just four neurons... okay?
network = tflearn.regression(network,
optimizer='adam',
loss='categorical_crossentropy',
name='target')
model = tflearn.DNN(network, tensorboard_verbose=0)
X, Y = getXY()
model.fit(X,
Y,
n_epoch=1,
validation_set=0.1,
show_metric=True,
snapshot_step=100)
import tensorflow as tf
import tflearn
import tflearn.datasets.mnist as mnist
mnist_data = mnist.read_data_sets(one_hot=True)
with tf.Graph().as_default():
# placeholders for data and labels
X = tf.placeholder(shape=(None, 784), dtype=tf.float32)
Y = tf.placeholder(shape=(None, 10), dtype=tf.float32)
net = tf.reshape(X, [-1, 28, 28, 1])
net = tflearn.conv_2d(net, 32, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.conv_2d(net, 64, 3, activation='relu')
net = tflearn.max_pool_2d(net, 2)
net = tflearn.local_response_normalization(net)
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 128, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 256, activation='tanh')
net = tflearn.dropout(net, 0.8)
net = tflearn.fully_connected(net, 10, activation='linear')
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(net, Y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
batch_size = 128
for epoch in range(2):
avg_cost = 0
total_batch = int(mnist_data.train.num_examples / batch_size)
