def build_deepvo(inputs,
is_training,
seq_length,
height,
width,
scope='deepvo'):
# print (inputs)
# inputs_list = tf.unstack(inputs)
# for inputs in inputs_list:
# pred = build_flownet(inputs, is_training=is_training)
#
with tf.variable_scope('timedistruted_cnn', reuse=tf.AUTO_REUSE):
print(inputs)
inputs = tf.reshape(inputs, (1, seq_length, height, width, 2))
net = core.input_data(shape=(None, seq_length, height, width, 2),
placeholder=inputs)
net = core.time_distributed(net, build_flownet, [inputs])
# net = core.time_distributed(net, conv.conv_2d, [32, 7, 2, 'same', 'relu'])
# net = core.time_distributed(net, conv.conv_2d, [64, 5, 2, 'same', 'relu'])
# net = core.time_distributed(net, conv.conv_2d, [128, 3, 2, 'same', 'relu'])
# net = core.time_distributed(net, conv.conv_2d, [256, 3, 2, 'same', 'relu'])
# net = core.time_distributed(net, conv.conv_2d, [256, 3, 2, 'same', 'relu'])
# net = core.time_distributed(net, conv.conv_2d, [256, 3, 2, 'same', 'relu'])
net = core.time_distributed(net, conv.global_max_pool)
with tf.variable_scope('rnn'):
net = recurrent.lstm(net,
n_units=124,
activation=tf.nn.relu,
return_seq=True,
name='lstm1')
net = recurrent.lstm(net,
n_units=124,
activation=tf.nn.relu,
return_seq=True,
name='lstm2')
net = core.time_distributed(net, core.fully_connected, [128, 'relu'])
net = core.time_distributed(net, core.fully_connected, [12])
pose, uncertainty = tf.split(net, 2, axis=2)
pose = tf.cast(pose, tf.float64)
print("pose output shape")
print(pose)
#pose = core.fully_connected(net, activation=tf.nn.relu, n_units=128)
#pose = core.fully_connected(net, n_units=6)
#pose = tf.cast(pose, tf.float64)
#print (pose)
#print (tf.trainable_variables())
return pose, uncertainty
def network(self):
in_layer = input_data([None, 1, self.str_len * 2 + 2, 1])
indices = in_layer[:, 0, :2, 0]
if self.emb > 1:
lstm1 = lstm(embedding(in_layer[:, 0, 2:, 0], 26, self.emb),
300,
return_seq=True)
else:
lstm1 = lstm(in_layer[:, 0, 2:, :], 300, return_seq=True)
# lstm branch
lstm2 = lstm(lstm1, 300, return_seq=True)
lstm3 = lstm(lstm2, 300, return_seq=True)
lstm4 = lstm(lstm3, 300)
# cnn branch
in_layer = bn(in_layer)
conv1 = conv_2d(in_layer, 64, [1, 7], 1)
norm1 = relu(bn(conv1))
block1 = self.residual_block(norm1, 128, [1, 3], 2, stride=2)
block2 = self.residual_block(block1, 256, [1, 3], 2, stride=2)
block3 = self.residual_block(block2, 512, [1, 3], 2)
block4 = self.residual_block(block3, 1024, [1, 3], 2)
n_out_filters = block4.get_shape().as_list()[-1]
gap = tf.reshape(global_avg_pool(block4), [-1, n_out_filters])
# fully-connected branch
fc_ind = fc(indices, 100, activation='tanh')
fc_ind2 = fc(fc_ind, 100, activation='tanh')
# merge lstm, conv, and fc layers
merged = tf.concat([lstm4, gap, fc_ind2], 1)
out = fc(merged, self.num_classes,
activation='softmax') # output layer
# describe optimization
net = regression(out,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=self.lr)
# build model
model = tflearn.DNN(net, tensorboard_verbose=2, tensorboard_dir='.')
return model
def get_network(): network = input_data(shape=[None, LEN_HISTORY], name="inp") network = reshape(network, [tf.shape(network)[0], LEN_HISTORY, 1], name="added_inp_dim") network = lstm(network, LEN_HISTORY, name="hidden", return_seq=True) network = [fully_connected(ts, 1, activation='softmax') for ts in network] network = merge(network, "concat", axis=1, name="concat_merge") network = network / tf.expand_dims(tf.reduce_mean(network, axis=1), 1, name="normed") network = regression(network, optimizer="sgd", loss=revenue) return network
def ProteinNet(str_len, emb, lr, num_classes):
in_layer = input_data([None, 1, str_len * 2 + 2, 1])
indices = in_layer[:, 0, :2, 0]
if emb > 1:
lstm1 = lstm(embedding(in_layer[:, 0, 2:, 0], 26, emb),
300,
return_seq=True)
else:
lstm1 = lstm(in_layer[:, 0, 2:, :], 300, return_seq=True)
# lstm branch
lstm2 = lstm(lstm1, 300, return_seq=True)
lstm3 = lstm(lstm2, 300, return_seq=True)
lstm4 = lstm(lstm3, 300)
# cnn branch
in_layer = bn(in_layer)
conv1 = conv_2d(in_layer, 64, [1, 10], 1)
norm1 = relu(bn(conv1))
conv2 = conv_2d(norm1, 128, [1, 6], 2)
norm2 = relu(bn(conv2))
conv3 = conv_2d(norm2, 256, [1, 3], 2)
norm3 = relu(bn(conv3))
gap = tf.reshape(global_avg_pool(norm3), [-1, 256])
# fully-connected branch
fc_ind = fc(indices, 50, activation='tanh')
fc_ind2 = fc(fc_ind, 50, activation='tanh')
# merge lstm, conv, and fc layers
merged = tf.concat([lstm4, gap, fc_ind2], 1)
out = fc(merged, num_classes, activation='softmax')
net = regression(out,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=lr)
model = tflearn.DNN(net, tensorboard_verbose=2, tensorboard_dir='.')
return model
def transform_embedded_sequences(self, embedded_sequences):
net = embedded_sequences
for i in range(1, self.params['layers'] + 1):
# if there are more lstms downstream - return sequences
return_sequences = i < self.params['layers']
net = lstm(net,
self.params['units'],
dropout=(self.params['dropout_rate'],self.params['rec_dropout_rate']),
return_seq=return_sequences)
preds = fully_connected(net, self.class_count, activation='softmax')
return preds
def cnnLSTM_model():
global model
filter_size_conv1 = 11
num_filters_conv1 = 5
filter_size_conv2 = 6
num_filters_conv2 = 10
filter_size_conv3 = 5
num_filters_conv3 = 5
filter_size_conv4 = 2
num_filters_conv4 = 2
lstm_units = 500
learning_rate = 1e-4
y_true = tf.placeholder(tf.float32,
shape=[None, num_classes],
name='y_true')
net = tflearn.input_data([None, 22, 64, 48, 1], name="input")
net = time_distributed(
net,
conv_2d,
args=[num_filters_conv1, filter_size_conv1, 1, 'same', 'tanh'])
net = time_distributed(net, max_pool_2d, args=[2])
net = time_distributed(
net,
conv_2d,
args=[num_filters_conv2, filter_size_conv2, 1, 'same', 'tanh'])
net = time_distributed(net, max_pool_2d, args=[2])
net = time_distributed(
net,
conv_2d,
args=[num_filters_conv3, filter_size_conv3, 1, 'same', 'tanh'])
net = time_distributed(net, max_pool_2d, args=[2])
net = time_distributed(net, flatten, args=['flat'])
net = lstm(net, lstm_units)
fc_layer = tflearn.fully_connected(net, num_classes, activation='softmax')
loss = tflearn.objectives.categorical_crossentropy(fc_layer, y_true)
network = regression(fc_layer,
optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001)
# Training
model = tflearn.DNN(network,
tensorboard_verbose=0,
checkpoint_path='gestureCNNLSTM.tfl.ckpt')
def typeSubtypeNameGeneratorModel(maxLength, charIndex, checkpoint_path='./generator_checkpoints/'):
'''
Recurrent network model for generating card types, subtypes, and names
Inputs:
maxLength: the maximum length for a generated sequence
charIndex: map from chars to the index they represent in a onehot encoding
checkpoint_path: path to save model after every epoch ('./generator_checkpoints/')
'''
network = input_data(shape=[None, maxLength, len(charIndex)])
network = lstm(network, 512, return_seq=True)
network = dropout(network, 0.5)
network = lstm(network, 512, return_seq=True)
network = dropout(network, 0.5)
network = lstm(network, 512)
network = dropout(network, 0.5)
network = fully_connected(network, len(charIndex), activation='softmax')
network = regression(network, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.001)
model = tflearn.SequenceGenerator(network, tensorboard_verbose=0, dictionary=charIndex,
seq_maxlen=maxLength, clip_gradients=5.0,
checkpoint_path='./generator_checkpoints/')
return model
def getLSTM(num_features, units, dropout):
network = input_data([None, 1, num_features])
for i, u in enumerate(units):
network = lstm(network,
u,
dropout=dropout,
return_seq=i != len(units) - 1)
network = fully_connected(
network, 10, activation="tanh") # this defaults to linear activation
network = fully_connected(
network, 1, activation=None) # this defaults to linear activation
network = regression(network,
optimizer='rmsprop',
learning_rate=0.01,
loss='mean_square')
return network
cnnlstmmodel = max_pool_2d(cnnlstmmodel, 2)
cnnlstmmodel = conv_2d(cnnlstmmodel, 256, 2, activation='relu')
cnnlstmmodel = max_pool_2d(cnnlstmmodel, 2)
cnnlstmmodel = conv_2d(cnnlstmmodel, 128, 2, activation='relu')
cnnlstmmodel = max_pool_2d(cnnlstmmodel, 2)
cnnlstmmodel = conv_2d(cnnlstmmodel, 64, 2, activation='relu')
cnnlstmmodel = max_pool_2d(cnnlstmmodel, 2)
cnnlstmmodel = conv_2d(cnnlstmmodel, 32, 2, activation='relu')
cnnlstmmodel = max_pool_2d(cnnlstmmodel, 2)
cnnlstmmodel = time_distributed(cnnlstmmodel, flatten, args=['flat'])
cnnlstmmodel = lstm(cnnlstmmodel, 1024)
cnnlstmmodel = fully_connected(cnnlstmmodel, 1000, activation='relu')
cnnlstmmodel = dropout(cnnlstmmodel, 0.7)
cnnlstmmodel = fully_connected(cnnlstmmodel, 10, activation='softmax')
cnnlstmmodel = regression(cnnlstmmodel,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='regression')
model = tflearn.DNN(cnnlstmmodel, tensorboard_verbose=0)
# Load Saved Model
model.load("TrainedModelCNNLSTM/CNNLSTMFIX.tfl")
def create_network(self):
print('function: create_network')
convnet = input_data(shape=[None, 6], name='input')
convnet = embedding(convnet, input_dim=10000, output_dim=128)
convnet = lstm(convnet, 128, dropout=0.8)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)
convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = conv_2d(convnet, 32, 5, activation='relu')
# convnet = max_pool_2d(convnet, 5)
# convnet = conv_2d(convnet, 32, 5, activation='relu')
# convnet = max_pool_2d(convnet, 5)
# convnet = conv_2d(convnet, 32, 5, activation='relu')
# convnet = max_pool_2d(convnet, 5)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = dropout(convnet, 0.5)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = dropout(convnet, 0.6)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = embedding(convnet, input_dim=256, output_dim=256)
# convnet = lstm(convnet, 256, dropout=0.8)
# convnet = embedding(convnet, input_dim=256, output_dim=255)
# convnet = lstm(convnet, 256, dropout=0.8)
# convnet = embedding(convnet, input_dim=256, output_dim=255)
# convnet = lstm(convnet, 256, dropout=0.8)
# convnet = embedding(convnet, input_dim=256, output_dim=255)
# convnet = lstm(convnet, 255, dropout=0.8)
# convnet = simple_rnn(convnet, 6, dropout=0.8)
# convnet = simple_rnn(convnet, 6, dropout=0.8)
# convnet = simple_rnn(convnet, 6, dropout=0.8)
# convnet = simple_rnn(convnet, 6, dropout=0.8)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = dropout(convnet, 0.8)
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = fully_connected(convnet, 1024, activation='relu')
# convnet = dropout(convnet, 0.8)
# convnet = fully_connected(convnet, 1024, activation='relu')
convnet = fully_connected(convnet, 3, activation='softmax')
convnet = regression(convnet,
optimizer='adam',
learning_rate=0.0001,
loss='categorical_crossentropy',
name='targets')
model = tflearn.DNN(convnet, tensorboard_dir='log')
return model
regularizer="L2")
# branch6 = conv_1d(network, 128, 6, padding='valid', activation='relu', regularizer="L2")
# branch7 = conv_1d(network, 128, 7, padding='valid', activation='relu', regularizer="L2")
# branch8 = conv_1d(network, 128, 8, padding='valid', activation='relu', regularizer="L2")
network = merge([branch1, branch2, branch3, branch4, branch5],
mode='concat',
axis=1)
network = tf.expand_dims(network, 2)
network = global_max_pool(network)
# network = fully_connected(network, 64, activation='tanh')
# network = dropout(network, 0.8)
network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.8)
network = tf.expand_dims(network, 2)
network = lstm(network, 128, return_seq=True)
network = lstm(network, 128)
network = fully_connected(network, 64, activation='relu')
network = dropout(network, 0.8)
network = fully_connected(network, 2, activation='tanh')
network = regression(network,
optimizer='adam',
learning_rate=0.001,
loss=concordance_cc,
name='target')
# Training
model = tflearn.DNN(network, tensorboard_verbose=0)
# model = tflearn.DNN(network, tensorboard_verbose=0)
model.load('./saved_model/cnn.tfl')
# model.fit(trainX, trainY, n_epoch=1, shuffle=True, validation_set=(evalX, evalY), show_metric=True, batch_size=128)
# model.save('./saved_model/cnn.tfl')
cv2.putText(textImage, "Pedicted Class : " + className, (30, 30),
cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
cv2.putText(textImage, "Confidence : " + str(confidence * 100) + '%',
(30, 100), cv2.FONT_HERSHEY_SIMPLEX, 1, (255, 255, 255), 2)
cv2.imshow("Statistics", textImage)
tf.reset_default_graph()
lstmmodel = input_data(shape=[None, 89, 100, 1], name='input')
lstmmodel = time_distributed(lstmmodel, dropout, args=[0.7])
lstmmodel = time_distributed(lstmmodel, flatten, args=['flat'])
lstmmodel = lstm(lstmmodel, 512)
lstmmodel = fully_connected(lstmmodel, 1000, activation='relu')
lstmmodel = dropout(lstmmodel, 0.7)
lstmmodel = fully_connected(lstmmodel, 10, activation='softmax')
lstmmodel = regression(lstmmodel,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy',
name='regression')
model = tflearn.DNN(lstmmodel, tensorboard_verbose=0)
# Load Saved Model
from tflearn.layers.recurrent import simple_rnn, lstm
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
X, Y, test_x, test_y = mnist.load_data(one_hot=True)
X = X.reshape([-1, 28, 28])
test_x = test_x.reshape([-1, 28, 28])
# X = X.transpose(X,[1,0,2])
# X = X.reshape(X,[-1,28])
# X = X.split(X,28,0)
net = input_data(shape=[None, 28, 28], name='input')
net = lstm(net, 128, dropout=0.8)
net = fully_connected(net, 10, activation='softmax')
net = regression(net,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy')
model = tflearn.DNN(net)
model.fit(X,
Y,
validation_set=(test_x, test_y),
show_metric=True,
batch_size=128,
n_epoch=3)
import tflearn
from tflearn.layers.recurrent import lstm
from tflearn.layers.core import input_data, fully_connected
from tflearn.layers.estimator import regression
import tflearn.datasets.mnist as mnist
trainX, trainY, testX, testY = mnist.load_data(data_dir='/path/to/MNIST_data',
one_hot=True)
trainX = trainX.reshape([-1, 784, 1])
testX = testX.reshape([-1, 784, 1])
net = input_data(shape=[None, 784, 1], name='input')
net = lstm(net, 128, activation='relu')
output = fully_connected(net, 10)
output = regression(output,
optimizer='Adam',
learning_rate=0.03,
loss='categorical_crossentropy')
model = tflearn.DNN(net, tensorboard_verbose=0)
model.fit(trainX,
trainY,
n_epoch=20,
validation_set=([testX, trainY]),
batch_size=128,
show_metric=True)
score = model.evaluate(testX, testY)
print('Test loss: ', score[0])
print('Test accuracy: ', score[1])