def test_dnn(self):
with tf.Graph().as_default():
X = [3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1]
Y = [1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3]
input = zqtflearn.input_data(shape=[None])
linear = zqtflearn.single_unit(input)
regression = zqtflearn.regression(linear, optimizer='sgd', loss='mean_square',
metric='R2', learning_rate=0.01)
m = zqtflearn.DNN(regression)
# Testing fit and predict
m.fit(X, Y, n_epoch=1000, show_metric=True, snapshot_epoch=False)
res = m.predict([3.2])[0]
self.assertGreater(res, 1.3, "DNN test (linear regression) failed! with score: " + str(res) + " expected > 1.3")
self.assertLess(res, 1.8, "DNN test (linear regression) failed! with score: " + str(res) + " expected < 1.8")
# Testing save method
m.save("test_dnn.zqtflearn")
self.assertTrue(os.path.exists("test_dnn.zqtflearn.index"))
with tf.Graph().as_default():
input = zqtflearn.input_data(shape=[None])
linear = zqtflearn.single_unit(input)
regression = zqtflearn.regression(linear, optimizer='sgd', loss='mean_square',
metric='R2', learning_rate=0.01)
m = zqtflearn.DNN(regression)
# Testing load method
m.load("test_dnn.zqtflearn")
res = m.predict([3.2])[0]
self.assertGreater(res, 1.3, "DNN test (linear regression) failed after loading model! score: " + str(res) + " expected > 1.3")
self.assertLess(res, 1.8, "DNN test (linear regression) failed after loading model! score: " + str(res) + " expected < 1.8")
def test_regression_placeholder(self):
'''
Check that regression does not duplicate placeholders
'''
with tf.Graph().as_default():
g = zqtflearn.input_data(shape=[None, 2])
g_nand = zqtflearn.fully_connected(g, 1, activation='linear')
with tf.name_scope("Y"):
Y_in = tf.placeholder(shape=[None, 1], dtype=tf.float32, name="Y")
zqtflearn.regression(g_nand, optimizer='sgd',
placeholder=Y_in,
learning_rate=2.,
loss='binary_crossentropy',
op_name="regression1",
name="Y")
# for this test, just use the same default trainable_vars
# in practice, this should be different for the two regressions
zqtflearn.regression(g_nand, optimizer='adam',
placeholder=Y_in,
learning_rate=2.,
loss='binary_crossentropy',
op_name="regression2",
name="Y")
self.assertEqual(len(tf.get_collection(tf.GraphKeys.TARGETS)), 1)
def test_sequencegenerator(self):
with tf.Graph().as_default():
text = "123456789101234567891012345678910123456789101234567891012345678910"
maxlen = 5
X, Y, char_idx = \
zqtflearn.data_utils.string_to_semi_redundant_sequences(text, seq_maxlen=maxlen, redun_step=3)
g = zqtflearn.input_data(shape=[None, maxlen, len(char_idx)])
g = zqtflearn.lstm(g, 32)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.fully_connected(g, len(char_idx), activation='softmax')
g = zqtflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.1)
m = zqtflearn.SequenceGenerator(g, dictionary=char_idx,
seq_maxlen=maxlen,
clip_gradients=5.0)
m.fit(X, Y, validation_set=0.1, n_epoch=100, snapshot_epoch=False)
res = m.generate(10, temperature=.5, seq_seed="12345")
#self.assertEqual(res, "123456789101234", "SequenceGenerator test failed! Generated sequence: " + res + " expected '123456789101234'")
# Testing save method
m.save("test_seqgen.zqtflearn")
self.assertTrue(os.path.exists("test_seqgen.zqtflearn.index"))
# Testing load method
m.load("test_seqgen.zqtflearn")
res = m.generate(10, temperature=.5, seq_seed="12345")
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 = zqtflearn.input_data(shape=[None, 4])
g = zqtflearn.reshape(g, new_shape=[-1, 2, 2, 1])
g = zqtflearn.conv_2d(g, 4, 2, activation='relu')
g = zqtflearn.max_pool_2d(g, 2)
g = zqtflearn.fully_connected(g, 2, activation='softmax')
g = zqtflearn.regression(g, optimizer='sgd', learning_rate=1.)
m = zqtflearn.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 = zqtflearn.input_data(shape=[None, 4])
g = zqtflearn.reshape(g, new_shape=[-1, 2, 2, 1])
g = zqtflearn.conv_2d(g, 4, 2)
g = zqtflearn.conv_2d(g, 4, 1)
g = zqtflearn.conv_2d_transpose(g, 4, 2, [2, 2])
g = zqtflearn.max_pool_2d(g, 2)
def test_core_layers(self):
X = [[0., 0.], [0., 1.], [1., 0.], [1., 1.]]
Y_nand = [[1.], [1.], [1.], [0.]]
Y_or = [[0.], [1.], [1.], [1.]]
# Graph definition
with tf.Graph().as_default():
# Building a network with 2 optimizers
g = zqtflearn.input_data(shape=[None, 2])
# Nand operator definition
g_nand = zqtflearn.fully_connected(g, 32, activation='linear')
g_nand = zqtflearn.fully_connected(g_nand, 32, activation='linear')
g_nand = zqtflearn.fully_connected(g_nand, 1, activation='sigmoid')
g_nand = zqtflearn.regression(g_nand, optimizer='sgd',
learning_rate=2.,
loss='binary_crossentropy')
# Or operator definition
g_or = zqtflearn.fully_connected(g, 32, activation='linear')
g_or = zqtflearn.fully_connected(g_or, 32, activation='linear')
g_or = zqtflearn.fully_connected(g_or, 1, activation='sigmoid')
g_or = zqtflearn.regression(g_or, optimizer='sgd',
learning_rate=2.,
loss='binary_crossentropy')
# XOR merging Nand and Or operators
g_xor = zqtflearn.merge([g_nand, g_or], mode='elemwise_mul')
# Training
m = zqtflearn.DNN(g_xor)
m.fit(X, [Y_nand, Y_or], n_epoch=400, snapshot_epoch=False)
# Testing
self.assertLess(m.predict([[0., 0.]])[0][0], 0.01)
self.assertGreater(m.predict([[0., 1.]])[0][0], 0.9)
self.assertGreater(m.predict([[1., 0.]])[0][0], 0.9)
self.assertLess(m.predict([[1., 1.]])[0][0], 0.01)
# Bulk Tests
with tf.Graph().as_default():
net = zqtflearn.input_data(shape=[None, 2])
net = zqtflearn.flatten(net)
net = zqtflearn.reshape(net, new_shape=[-1])
net = zqtflearn.activation(net, 'relu')
net = zqtflearn.dropout(net, 0.5)
net = zqtflearn.single_unit(net)
def __init__(self):
# Building deep neural network
network = zqtflearn.input_data(shape=[None, 784], name="input")
network = self.make_core_network(network)
# Regression using SGD with learning rate decay and Top-3 accuracy
sgd = zqtflearn.SGD(learning_rate=0.1, lr_decay=0.96, decay_step=1000)
top_k = zqtflearn.metrics.Top_k(3)
network = zqtflearn.regression(network, optimizer=sgd, metric=top_k,
loss='categorical_crossentropy', name="target")
model = zqtflearn.DNN(network, tensorboard_verbose=0)
self.model = model
def test_recurrent_layers(self):
X = [[1, 3, 5, 7], [2, 4, 8, 10], [1, 5, 9, 11], [2, 6, 8, 0]]
Y = [[0., 1.], [1., 0.], [0., 1.], [1., 0.]]
with tf.Graph().as_default():
g = zqtflearn.input_data(shape=[None, 4])
g = zqtflearn.embedding(g, input_dim=12, output_dim=4)
g = zqtflearn.lstm(g, 6)
g = zqtflearn.fully_connected(g, 2, activation='softmax')
g = zqtflearn.regression(g, optimizer='sgd', learning_rate=1.)
m = zqtflearn.DNN(g)
m.fit(X, Y, n_epoch=300, snapshot_epoch=False)
self.assertGreater(m.predict([[5, 9, 11, 1]])[0][1], 0.9)
def test_sequencegenerator_words(self):
with tf.Graph().as_default():
text = ["hello","world"]*100
word_idx = {"hello": 0, "world": 1}
maxlen = 2
vec = [x for x in map(word_idx.get, text) if x is not None]
sequences = []
next_words = []
for i in range(0, len(vec) - maxlen, 3):
sequences.append(vec[i: i + maxlen])
next_words.append(vec[i + maxlen])
X = np.zeros((len(sequences), maxlen, len(word_idx)), dtype=np.bool)
Y = np.zeros((len(sequences), len(word_idx)), dtype=np.bool)
for i, seq in enumerate(sequences):
for t, idx in enumerate(seq):
X[i, t, idx] = True
Y[i, next_words[i]] = True
g = zqtflearn.input_data(shape=[None, maxlen, len(word_idx)])
g = zqtflearn.lstm(g, 32)
g = zqtflearn.dropout(g, 0.5)
g = zqtflearn.fully_connected(g, len(word_idx), activation='softmax')
g = zqtflearn.regression(g, optimizer='adam', loss='categorical_crossentropy',
learning_rate=0.1)
m = zqtflearn.SequenceGenerator(g, dictionary=word_idx,
seq_maxlen=maxlen,
clip_gradients=5.0)
m.fit(X, Y, validation_set=0.1, n_epoch=100, snapshot_epoch=False)
res = m.generate(4, temperature=.5, seq_seed=["hello","world"])
res_str = " ".join(res[-2:])
self.assertEqual(res_str, "hello world", "SequenceGenerator (word level) test failed! Generated sequence: " + res_str + " expected 'hello world'")
# Testing save method
m.save("test_seqgen_word.zqtflearn")
self.assertTrue(os.path.exists("test_seqgen_word.zqtflearn.index"))
# Testing load method
m.load("test_seqgen_word.zqtflearn")
res = m.generate(4, temperature=.5, seq_seed=["hello","world"])
res_str = " ".join(res[-2:])
self.assertEqual(res_str, "hello world", "Reloaded SequenceGenerator (word level) test failed! Generated sequence: " + res_str + " expected 'hello world'")
def test_feed_dict_no_None(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 = zqtflearn.input_data(shape=[None, 4], name="X_in")
g = zqtflearn.reshape(g, new_shape=[-1, 2, 2, 1])
g = zqtflearn.conv_2d(g, 4, 2)
g = zqtflearn.conv_2d(g, 4, 1)
g = zqtflearn.max_pool_2d(g, 2)
g = zqtflearn.fully_connected(g, 2, activation='softmax')
g = zqtflearn.regression(g, optimizer='sgd', learning_rate=1.)
m = zqtflearn.DNN(g)
def do_fit():
m.fit({"X_in": X, 'non_existent': X}, Y, n_epoch=30, snapshot_epoch=False)
self.assertRaisesRegexp(Exception, "Feed dict asks for variable named 'non_existent' but no such variable is known to exist", do_fit)
def build_simple_model(self):
"""Build a simple model for test
Returns:
DNN, [ (input layer name, input placeholder, input data) ], Target data
"""
inputPlaceholder1, inputPlaceholder2 = \
tf.placeholder(tf.float32, (1, 1), name = "input1"), tf.placeholder(tf.float32, (1, 1), name = "input2")
input1 = zqtflearn.input_data(placeholder=inputPlaceholder1)
input2 = zqtflearn.input_data(placeholder=inputPlaceholder2)
network = zqtflearn.merge([input1, input2], "sum")
network = zqtflearn.reshape(network, (1, 1))
network = zqtflearn.fully_connected(network, 1)
network = zqtflearn.regression(network)
return (
zqtflearn.DNN(network),
[("input1:0", inputPlaceholder1, self.INPUT_DATA_1),
("input2:0", inputPlaceholder2, self.INPUT_DATA_2)],
self.TARGET,
)
def build_model(self, learning_rate=[0.001, 0.01]):
'''
Model - wide and deep - built using zqtflearn
'''
n_cc = len(self.continuous_columns)
n_cc = 108
input_shape = [None, n_cc]
if self.verbose:
print("=" * 77 + " Model %s (type=%s)" %
(self.name, self.model_type))
print(" Input placeholder shape=%s" % str(input_shape))
wide_inputs = zqtflearn.input_data(shape=input_shape, name="wide_X")
deep_inputs = zqtflearn.input_data(shape=[None, 1], name="deep_X")
if not isinstance(learning_rate, list):
learning_rate = [learning_rate, learning_rate] # wide, deep
if self.verbose:
print(" Learning rates (wide, deep)=%s" % learning_rate)
with tf.name_scope(
"Y"): # placeholder for target variable (i.e. trainY input)
Y_in = tf.placeholder(shape=[None, 1], dtype=tf.float32, name="Y")
with tf.variable_op_scope([wide_inputs], None, "cb_unit",
reuse=False) as scope:
central_bias = zqtflearn.variables.variable(
'central_bias',
shape=[1],
initializer=tf.constant_initializer(np.random.randn()),
trainable=True,
restore=True)
tf.add_to_collection(tf.GraphKeys.LAYER_VARIABLES + '/cb_unit',
central_bias)
if 'wide' in self.model_type:
wide_network = self.wide_model(wide_inputs, n_cc)
network = wide_network
wide_network_with_bias = tf.add(wide_network,
central_bias,
name="wide_with_bias")
if 'deep' in self.model_type:
deep_network = self.deep_model(
wide_inputs, deep_inputs, n_cc
) # 这里面是wide inputs,在这个函数内部wide_inputs,会和deep_model制造的输入相合并。
deep_network_with_bias = tf.add(deep_network,
central_bias,
name="deep_with_bias")
if 'wide' in self.model_type:
network = tf.add(wide_network, deep_network)
if self.verbose:
print("Wide + deep model network %s" % network)
else:
network = deep_network
network = tf.add(network, central_bias, name="add_central_bias")
# add validation monitor summaries giving confusion matrix entries
with tf.name_scope('Monitors'):
predictions = tf.cast(tf.greater(network, 0), tf.int64)
print("predictions=%s" % predictions)
Ybool = tf.cast(Y_in, tf.bool)
print("Ybool=%s" % Ybool)
pos = tf.boolean_mask(predictions, Ybool)
neg = tf.boolean_mask(predictions, ~Ybool)
psize = tf.cast(tf.shape(pos)[0], tf.int64)
nsize = tf.cast(tf.shape(neg)[0], tf.int64)
true_positive = tf.reduce_sum(pos, name="true_positive")
false_negative = tf.subtract(psize,
true_positive,
name="false_negative")
false_positive = tf.reduce_sum(neg, name="false_positive")
true_negative = tf.subtract(nsize,
false_positive,
name="true_negative")
overall_accuracy = tf.truediv(tf.add(true_positive, true_negative),
tf.add(nsize, psize),
name="overall_accuracy")
vmset = [
true_positive, true_negative, false_positive, false_negative,
overall_accuracy
]
trainable_vars = tf.trainable_variables()
tv_deep = [v for v in trainable_vars if v.name.startswith('deep_')]
tv_wide = [v for v in trainable_vars if v.name.startswith('wide_')]
if self.verbose:
print("DEEP trainable_vars")
for v in tv_deep:
print(" Variable %s: %s" % (v.name, v))
print("WIDE trainable_vars")
for v in tv_wide:
print(" Variable %s: %s" % (v.name, v))
# if 'wide' in self.model_type:
# if not 'deep' in self.model_type:
# tv_wide.append(central_bias)
# zqtflearn.regression(wide_network_with_bias,
# placeholder=Y_in,
# optimizer='sgd',
# loss='roc_auc_score',
# #loss='binary_crossentropy',
# metric="accuracy",
# learning_rate=learning_rate[0],
# validation_monitors=vmset,
# trainable_vars=tv_wide,
# op_name="wide_regression",
# name="Y")
#
# if 'deep' in self.model_type:
# if not 'wide' in self.model_type:
# tv_wide.append(central_bias)
# zqtflearn.regression(deep_network_with_bias,
# placeholder=Y_in,
# optimizer='adam',
# loss='roc_auc_score',
# #loss='binary_crossentropy',
# metric="accuracy",
# learning_rate=learning_rate[1],
# validation_monitors=vmset if not 'wide' in self.model_type else None,
# trainable_vars=tv_deep,
# op_name="deep_regression",
# name="Y")
if self.model_type == 'wide+deep': # learn central bias separately for wide+deep
zqtflearn.regression(
network,
placeholder=Y_in,
optimizer='adam',
#loss="roc_auc_score",
loss='binary_crossentropy',
metric="accuracy",
validation_monitors=vmset,
learning_rate=learning_rate[0], # use wide learning rate
#trainable_vars=[central_bias], #[tv_deep,tv_wide,central_bias] # None
op_name="central_bias_regression",
name="Y")
self.model = zqtflearn.DNN(
network,
tensorboard_verbose=self.tensorboard_verbose,
max_checkpoints=self.max_checkpoints,
checkpoint_path="%s/%s.tfl" % (self.checkpoints_dir, self.name),
tensorboard_dir=self.tensorboard_dir)
# tensorboard_dir="/tmp/tflearn_logs/" zqtflearn.DNN 我把他改为当前目录下的了，这样也比较好规范
if 'deep' in self.model_type:
embeddingWeights = zqtflearn.get_layer_variables_by_name(
'deep_video_ids_embed')[0]
# CUSTOM_WEIGHT = pickle.load("Haven't deal")
# emb = np.array(CUSTOM_WEIGHT, dtype=np.float32)
# emb = self.embedding
new_emb_t = tf.convert_to_tensor(self.embedding)
self.model.set_weights(embeddingWeights, new_emb_t)
if self.verbose:
print("Target variables:")
for v in tf.get_collection(tf.GraphKeys.TARGETS):
print(" variable %s: %s" % (v.name, v))
print("=" * 77)
print("model build finish")
scope='decoder_h')
decoder = zqtflearn.fully_connected(decoder, original_dim, activation='sigmoid',
scope='decoder_out')
# Define VAE Loss
def vae_loss(x_reconstructed, x_true):
# Reconstruction loss
encode_decode_loss = x_true * tf.log(1e-10 + x_reconstructed) \
+ (1 - x_true) * tf.log(1e-10 + 1 - x_reconstructed)
encode_decode_loss = -tf.reduce_sum(encode_decode_loss, 1)
# KL Divergence loss
kl_div_loss = 1 + z_std - tf.square(z_mean) - tf.exp(z_std)
kl_div_loss = -0.5 * tf.reduce_sum(kl_div_loss, 1)
return tf.reduce_mean(encode_decode_loss + kl_div_loss)
net = zqtflearn.regression(decoder, optimizer='rmsprop', learning_rate=0.001,
loss=vae_loss, metric=None, name='target_images')
# We will need 2 models, one for training that will learn the latent
# representation, and one that can take random normal noise as input and
# use the decoder part of the network to generate an image
# Train the VAE
training_model = zqtflearn.DNN(net, tensorboard_verbose=0)
training_model.fit({'input_images': X}, {'target_images': X}, n_epoch=100,
validation_set=(testX, testX), batch_size=256, run_id="vae")
# Build an image generator (re-using the decoding layers)
# Input data is a normal (gaussian) random distribution (with dim = latent_dim)
input_noise = zqtflearn.input_data(shape=[None, latent_dim], name='input_noise')
decoder = zqtflearn.fully_connected(input_noise, hidden_dim, activation='relu',
scope='decoder_h', reuse=True)
def build_model(self, learning_rate=[0.001, 0.01]):
'''
Model - wide and deep - built using zqtflearn
'''
n_cc = len(self.continuous_columns)
n_categories = 1 # two categories: is_idv and is_not_idv
input_shape = [None, n_cc]
if self.verbose:
print ("="*77 + " Model %s (type=%s)" % (self.name, self.model_type))
print (" Input placeholder shape=%s" % str(input_shape))
wide_inputs = zqtflearn.input_data(shape=input_shape, name="wide_X")
if not isinstance(learning_rate, list):
learning_rate = [learning_rate, learning_rate] # wide, deep
if self.verbose:
print (" Learning rates (wide, deep)=%s" % learning_rate)
with tf.name_scope("Y"): # placeholder for target variable (i.e. trainY input)
Y_in = tf.placeholder(shape=[None, 1], dtype=tf.float32, name="Y")
with tf.variable_scope(None, "cb_unit", [wide_inputs]) as scope:
central_bias = zqtflearn.variables.variable('central_bias', shape=[1],
initializer=tf.constant_initializer(np.random.randn()),
trainable=True, restore=True)
tf.add_to_collection(tf.GraphKeys.LAYER_VARIABLES + '/cb_unit', central_bias)
if 'wide' in self.model_type:
wide_network = self.wide_model(wide_inputs, n_cc)
network = wide_network
wide_network_with_bias = tf.add(wide_network, central_bias, name="wide_with_bias")
if 'deep' in self.model_type:
deep_network = self.deep_model(wide_inputs, n_cc)
deep_network_with_bias = tf.add(deep_network, central_bias, name="deep_with_bias")
if 'wide' in self.model_type:
network = tf.add(wide_network, deep_network)
if self.verbose:
print ("Wide + deep model network %s" % network)
else:
network = deep_network
network = tf.add(network, central_bias, name="add_central_bias")
# add validation monitor summaries giving confusion matrix entries
with tf.name_scope('Monitors'):
predictions = tf.cast(tf.greater(network, 0), tf.int64)
print ("predictions=%s" % predictions)
Ybool = tf.cast(Y_in, tf.bool)
print ("Ybool=%s" % Ybool)
pos = tf.boolean_mask(predictions, Ybool)
neg = tf.boolean_mask(predictions, ~Ybool)
psize = tf.cast(tf.shape(pos)[0], tf.int64)
nsize = tf.cast(tf.shape(neg)[0], tf.int64)
true_positive = tf.reduce_sum(pos, name="true_positive")
false_negative = tf.subtract(psize, true_positive, name="false_negative")
false_positive = tf.reduce_sum(neg, name="false_positive")
true_negative = tf.subtract(nsize, false_positive, name="true_negative")
overall_accuracy = tf.truediv(tf.add(true_positive, true_negative), tf.add(nsize, psize), name="overall_accuracy")
vmset = [true_positive, true_negative, false_positive, false_negative, overall_accuracy]
trainable_vars = tf.trainable_variables()
tv_deep = [v for v in trainable_vars if v.name.startswith('deep_')]
tv_wide = [v for v in trainable_vars if v.name.startswith('wide_')]
if self.verbose:
print ("DEEP trainable_vars")
for v in tv_deep:
print (" Variable %s: %s" % (v.name, v))
print ("WIDE trainable_vars")
for v in tv_wide:
print (" Variable %s: %s" % (v.name, v))
if 'wide' in self.model_type:
if not 'deep' in self.model_type:
tv_wide.append(central_bias)
zqtflearn.regression(wide_network_with_bias,
placeholder=Y_in,
optimizer='sgd',
#loss='roc_auc_score',
loss='binary_crossentropy',
metric="accuracy",
learning_rate=learning_rate[0],
validation_monitors=vmset,
trainable_vars=tv_wide,
op_name="wide_regression",
name="Y")
if 'deep' in self.model_type:
if not 'wide' in self.model_type:
tv_wide.append(central_bias)
zqtflearn.regression(deep_network_with_bias,
placeholder=Y_in,
optimizer='adam',
#loss='roc_auc_score',
loss='binary_crossentropy',
metric="accuracy",
learning_rate=learning_rate[1],
validation_monitors=vmset if not 'wide' in self.model_type else None,
trainable_vars=tv_deep,
op_name="deep_regression",
name="Y")
if self.model_type=='wide+deep': # learn central bias separately for wide+deep
zqtflearn.regression(network,
placeholder=Y_in,
optimizer='adam',
loss='binary_crossentropy',
metric="accuracy",
learning_rate=learning_rate[0], # use wide learning rate
trainable_vars=[central_bias],
op_name="central_bias_regression",
name="Y")
self.model = zqtflearn.DNN(network,
tensorboard_verbose=self.tensorboard_verbose,
max_checkpoints=5,
checkpoint_path="%s/%s.tfl" % (self.checkpoints_dir, self.name),
)
if self.verbose:
print ("Target variables:")
for v in tf.get_collection(tf.GraphKeys.TARGETS):
print (" variable %s: %s" % (v.name, v))
print ("="*77)
def test_dnn_loading_scope(self):
with tf.Graph().as_default():
X = [
3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,
7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1
]
Y = [
1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,
2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3
]
input = zqtflearn.input_data(shape=[None])
linear = zqtflearn.single_unit(input)
regression = zqtflearn.regression(linear,
optimizer='sgd',
loss='mean_square',
metric='R2',
learning_rate=0.01)
m = zqtflearn.DNN(regression)
# Testing fit and predict
m.fit(X, Y, n_epoch=1000, show_metric=True, snapshot_epoch=False)
res = m.predict([3.2])[0]
self.assertGreater(
res, 1.3, "DNN test (linear regression) failed! with score: " +
str(res) + " expected > 1.3")
self.assertLess(
res, 1.8, "DNN test (linear regression) failed! with score: " +
str(res) + " expected < 1.8")
# Testing save method
m.save("test_dnn.zqtflearn")
self.assertTrue(os.path.exists("test_dnn.zqtflearn.index"))
# Testing loading, with change of variable scope (saved with no scope, now loading into scopeA)
with tf.Graph().as_default(): # start with clear graph
with tf.variable_scope("scopeA") as scope:
input = zqtflearn.input_data(shape=[None])
linear = zqtflearn.single_unit(input)
regression = zqtflearn.regression(linear,
optimizer='sgd',
loss='mean_square',
metric='R2',
learning_rate=0.01)
m = zqtflearn.DNN(regression)
def try_load():
m.load("test_dnn.zqtflearn")
self.assertRaises(
tf.errors.NotFoundError,
try_load) # fails, since names in file don't have "scopeA"
m.load("test_dnn.zqtflearn", variable_name_map=(
"scopeA/",
"")) # succeeds, because variable names are rewritten
res = m.predict([3.2])[0]
self.assertGreater(
res, 1.3,
"DNN test (linear regression) failed after loading model! score: "
+ str(res) + " expected > 1.3")
self.assertLess(
res, 1.8,
"DNN test (linear regression) failed after loading model! score: "
+ str(res) + " expected < 1.8")
import zqtflearn
# Regression data
X = [
3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167, 7.042, 10.791,
5.313, 7.997, 5.654, 9.27, 3.1
]
Y = [
1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221, 2.827,
3.465, 1.65, 2.904, 2.42, 2.94, 1.3
]
# Linear Regression graph
input_ = zqtflearn.input_data(shape=[None])
linear = zqtflearn.single_unit(input_)
regression = zqtflearn.regression(linear,
optimizer='sgd',
loss='mean_square',
metric='R2',
learning_rate=0.01)
m = zqtflearn.DNN(regression)
m.fit(X, Y, n_epoch=1000, show_metric=True, snapshot_epoch=False)
print("\nRegression result:")
print("Y = " + str(m.get_weights(linear.W)) + "*X + " +
str(m.get_weights(linear.b)))
print("\nTest prediction for x = 3.2, 3.3, 3.4:")
print(m.predict([3.2, 3.3, 3.4]))
# should output (close, not exact) y = [1.5315033197402954, 1.5585315227508545, 1.5855598449707031]
# Building Residual Network
net = zqtflearn.input_data(shape=[None, 28, 28, 1])
net = zqtflearn.conv_2d(net, 64, 3, activation='relu', bias=False)
# Residual blocks
net = zqtflearn.residual_bottleneck(net, 3, 16, 64)
net = zqtflearn.residual_bottleneck(net, 1, 32, 128, downsample=True)
net = zqtflearn.residual_bottleneck(net, 2, 32, 128)
net = zqtflearn.residual_bottleneck(net, 1, 64, 256, downsample=True)
net = zqtflearn.residual_bottleneck(net, 2, 64, 256)
net = zqtflearn.batch_normalization(net)
net = zqtflearn.activation(net, 'relu')
net = zqtflearn.global_avg_pool(net)
# Regression
net = zqtflearn.fully_connected(net, 10, activation='softmax')
net = zqtflearn.regression(net,
optimizer='momentum',
loss='categorical_crossentropy',
learning_rate=0.1)
# Training
model = zqtflearn.DNN(net,
checkpoint_path='model_resnet_mnist',
max_checkpoints=10,
tensorboard_verbose=0)
model.fit(X,
Y,
n_epoch=100,
validation_set=(testX, testY),
show_metric=True,
batch_size=256,
run_id='resnet_mnist')
# -*- coding: utf-8 -*-
"""
MNIST Classification using RNN over images pixels. A picture is
representated as a sequence of pixels, coresponding to an image's
width (timestep) and height (number of sequences).
"""
from __future__ import division, print_function, absolute_import
import numpy as np
import zqtflearn
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
X = np.reshape(X, (-1, 28, 28))
testX = np.reshape(testX, (-1, 28, 28))
net = zqtflearn.input_data(shape=[None, 28, 28])
net = zqtflearn.lstm(net, 128, return_seq=True)
net = zqtflearn.lstm(net, 128)
net = zqtflearn.fully_connected(net, 10, activation='softmax')
net = zqtflearn.regression(net, optimizer='adam',
loss='categorical_crossentropy', name="output1")
model = zqtflearn.DNN(net, tensorboard_verbose=2)
model.fit(X, Y, n_epoch=1, validation_set=0.1, show_metric=True,
snapshot_step=100)
img_aug.add_random_flip_leftright()
img_aug.add_random_crop([32, 32], padding=4)
# Building Residual Network
net = zqtflearn.input_data(shape=[None, 32, 32, 3],
data_preprocessing=img_prep,
data_augmentation=img_aug)
net = zqtflearn.conv_2d(net, 16, 3, regularizer='L2', weight_decay=0.0001)
net = zqtflearn.residual_block(net, n, 16)
net = zqtflearn.residual_block(net, 1, 32, downsample=True)
net = zqtflearn.residual_block(net, n - 1, 32)
net = zqtflearn.residual_block(net, 1, 64, downsample=True)
net = zqtflearn.residual_block(net, n - 1, 64)
net = zqtflearn.batch_normalization(net)
net = zqtflearn.activation(net, 'relu')
net = zqtflearn.global_avg_pool(net)
# Regression
net = zqtflearn.fully_connected(net, 10, activation='softmax')
mom = zqtflearn.Momentum(0.1, lr_decay=0.1, decay_step=32000, staircase=True)
net = zqtflearn.regression(net, optimizer=mom,
loss='categorical_crossentropy')
# Training
model = zqtflearn.DNN(net, checkpoint_path='model_resnet_cifar10',
max_checkpoints=10, tensorboard_verbose=0,
clip_gradients=0.)
model.fit(X, Y, n_epoch=200, validation_set=(testX, testY),
snapshot_epoch=False, snapshot_step=500,
show_metric=True, batch_size=128, shuffle=True,
run_id='resnet_cifar10')
def build_model(self, learning_rate=[0.001, 0.01]):
'''
Model - wide and deep - built using tflearn
'''
n_cc = len(self.continuous_columns)
n_cc = 108
input_shape = [None, n_cc]
if self.verbose:
print("=" * 77 + " Model %s (type=%s)" %
(self.name, self.model_type))
print(" Input placeholder shape=%s" % str(input_shape))
wide_inputs = zqtflearn.input_data(shape=input_shape, name="wide_X")
if not isinstance(learning_rate, list):
learning_rate = [learning_rate, learning_rate] # wide, deep
if self.verbose:
print(" Learning rates (wide, deep)=%s" % learning_rate)
with tf.name_scope(
"Y"): # placeholder for target variable (i.e. trainY input)
Y_in = tf.placeholder(shape=[None, 1], dtype=tf.float32, name="Y")
with tf.variable_op_scope([wide_inputs], None, "cb_unit",
reuse=False) as scope:
central_bias = zqtflearn.variables.variable(
'central_bias',
shape=[1],
initializer=tf.constant_initializer(np.random.randn()),
trainable=True,
restore=True)
tf.add_to_collection(tf.GraphKeys.LAYER_VARIABLES + '/cb_unit',
central_bias)
wide_network = self.wide_model(wide_inputs, n_cc)
network = wide_network
network = tf.add(network, central_bias, name="add_central_bias")
# add validation monitor summaries giving confusion matrix entries
with tf.name_scope('Monitors'):
predictions = tf.cast(tf.greater(network, 0), tf.int64)
print("predictions=%s" % predictions)
Ybool = tf.cast(Y_in, tf.bool)
print("Ybool=%s" % Ybool)
pos = tf.boolean_mask(predictions, Ybool)
neg = tf.boolean_mask(predictions, ~Ybool)
psize = tf.cast(tf.shape(pos)[0], tf.int64)
nsize = tf.cast(tf.shape(neg)[0], tf.int64)
true_positive = tf.reduce_sum(pos, name="true_positive")
false_negative = tf.subtract(psize,
true_positive,
name="false_negative")
false_positive = tf.reduce_sum(neg, name="false_positive")
true_negative = tf.subtract(nsize,
false_positive,
name="true_negative")
overall_accuracy = tf.truediv(tf.add(true_positive, true_negative),
tf.add(nsize, psize),
name="overall_accuracy")
vmset = [
true_positive, true_negative, false_positive, false_negative,
overall_accuracy
]
zqtflearn.regression(
network,
placeholder=Y_in,
optimizer='adam',
#loss="roc_auc_score",
loss='binary_crossentropy',
metric="accuracy",
learning_rate=learning_rate[0], # use wide learning rate
# trainable_vars=[central_bias],
validation_monitors=vmset,
op_name="central_bias_regression",
name="Y")
self.model = zqtflearn.DNN(
network,
tensorboard_verbose=self.tensorboard_verbose,
max_checkpoints=self.max_checkpoints,
checkpoint_path="%s/%s.tfl" % (self.checkpoints_dir, self.name),
tensorboard_dir=self.tensorboard_dir)
if self.verbose:
print("Target variables:")
for v in tf.get_collection(tf.GraphKeys.TARGETS):
print(" variable %s: %s" % (v.name, v))
print("=" * 77)
# X, Y = image_preloader(data_dir, image_shape=(224, 224), mode='folder',
# categorical_labels=True, normalize=True,
# files_extension=['.jpg', '.png'], filter_channel=True)
num_classes = 10 # num of your dataset
# VGG preprocessing
img_prep = ImagePreprocessing()
img_prep.add_featurewise_zero_center(mean=[123.68, 116.779, 103.939],
per_channel=True)
# VGG Network
x = zqtflearn.input_data(shape=[None, 224, 224, 3], name='input',
data_preprocessing=img_prep)
softmax = vgg16(x, num_classes)
regression = zqtflearn.regression(softmax, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=0.001, restore=False)
model = zqtflearn.DNN(regression, checkpoint_path='vgg-finetuning',
max_checkpoints=3, tensorboard_verbose=2,
tensorboard_dir="./logs")
model_file = os.path.join(model_path, "vgg16.zqtflearn")
model.load(model_file, weights_only=True)
# Start finetuning
model.fit(X, Y, n_epoch=10, validation_set=0.1, shuffle=True,
show_metric=True, batch_size=64, snapshot_epoch=False,
snapshot_step=200, run_id='vgg-finetuning')
model.save('your-task-model-retrained-by-vgg')
import tensorflow as tf
import zqtflearn
# Logical NOT operator
X = [[0.], [1.]]
Y = [[1.], [0.]]
# Graph definition
with tf.Graph().as_default():
g = zqtflearn.input_data(shape=[None, 1])
g = zqtflearn.fully_connected(g, 128, activation='linear')
g = zqtflearn.fully_connected(g, 128, activation='linear')
g = zqtflearn.fully_connected(g, 1, activation='sigmoid')
g = zqtflearn.regression(g,
optimizer='sgd',
learning_rate=2.,
loss='mean_square')
# Model training
m = zqtflearn.DNN(g)
m.fit(X, Y, n_epoch=100, snapshot_epoch=False)
# Test model
print("Testing NOT operator")
print("NOT 0:", m.predict([[0.]]))
print("NOT 1:", m.predict([[1.]]))
# Logical OR operator
X = [[0., 0.], [0., 1.], [1., 0.], [1., 1.]]
Y = [[0.], [1.], [1.], [1.]]
# Converting 'sex' field to float (id is 1 after removing labels column)
passengers[i][1] = 1. if passengers[i][1] == 'female' else 0.
return np.array(passengers, dtype=np.float32)
# Ignore 'name' and 'ticket' columns (id 1 & 6 of data array)
to_ignore=[1, 6]
# Preprocess data
data = preprocess(data, to_ignore)
# Build neural network
net = zqtflearn.input_data(shape=[None, 6])
net = zqtflearn.fully_connected(net, 32)
net = zqtflearn.fully_connected(net, 32)
net = zqtflearn.fully_connected(net, 2, activation='softmax')
net = zqtflearn.regression(net)
# Define model
model = zqtflearn.DNN(net)
# Start training (apply gradient descent algorithm)
model.fit(data, labels, n_epoch=10, batch_size=16, show_metric=True)
# Let's create some data for DiCaprio and Winslet
dicaprio = [3, 'Jack Dawson', 'male', 19, 0, 0, 'N/A', 5.0000]
winslet = [1, 'Rose DeWitt Bukater', 'female', 17, 1, 2, 'N/A', 100.0000]
# Preprocess data
dicaprio, winslet = preprocess([dicaprio, winslet], to_ignore)
# Predict surviving chances (class 1 results)
pred = model.predict([dicaprio, winslet])
print("DiCaprio Surviving Rate:", pred[0][1])
print("Winslet Surviving Rate:", pred[1][1])
disc_net = tf.concat([disc_fake, disc_real], axis=0)
# Build Stacked Generator/Discriminator
gen_net = generator(gen_input, reuse=True)
stacked_gan_net = discriminator(gen_net, reuse=True)
# Build Training Ops for both Generator and Discriminator.
# Each network optimization should only update its own variable, thus we need
# to retrieve each network variables (with get_layer_variables_by_scope).
disc_vars = zqtflearn.get_layer_variables_by_scope('Discriminator')
# We need 2 target placeholders, for both the real and fake image target.
disc_target = zqtflearn.multi_target_data(
['target_disc_fake', 'target_disc_real'], shape=[None, 2])
disc_model = zqtflearn.regression(disc_net,
optimizer='adam',
placeholder=disc_target,
loss='categorical_crossentropy',
trainable_vars=disc_vars,
batch_size=64,
name='target_disc',
op_name='DISC')
gen_vars = zqtflearn.get_layer_variables_by_scope('Generator')
gan_model = zqtflearn.regression(stacked_gan_net,
optimizer='adam',
loss='categorical_crossentropy',
trainable_vars=gen_vars,
batch_size=64,
name='target_gen',
op_name='GEN')
# Define GAN model, that output the generated images.
gan = zqtflearn.DNN(gan_model)
gen_sample = generator(gen_input)
disc_real = discriminator(disc_input)
disc_fake = discriminator(gen_sample, reuse=True)
# Define Loss
disc_loss = -tf.reduce_mean(tf.log(disc_real) + tf.log(1. - disc_fake))
gen_loss = -tf.reduce_mean(tf.log(disc_fake))
# Build Training Ops for both Generator and Discriminator.
# Each network optimization should only update its own variable, thus we need
# to retrieve each network variables (with get_layer_variables_by_scope) and set
# 'placeholder=None' because we do not need to feed any target.
gen_vars = zqtflearn.get_layer_variables_by_scope('Generator')
gen_model = zqtflearn.regression(gen_sample, placeholder=None, optimizer='adam',
loss=gen_loss, trainable_vars=gen_vars,
batch_size=64, name='target_gen', op_name='GEN')
disc_vars = zqtflearn.get_layer_variables_by_scope('Discriminator')
disc_model = zqtflearn.regression(disc_real, placeholder=None, optimizer='adam',
loss=disc_loss, trainable_vars=disc_vars,
batch_size=64, name='target_disc', op_name='DISC')
# Define GAN model, that output the generated images.
gan = zqtflearn.DNN(gen_model)
# Training
# Generate noise to feed to the generator
z = np.random.uniform(-1., 1., size=[total_samples, z_dim])
# Start training, feed both noise and real images.
gan.fit(X_inputs={gen_input: z, disc_input: X},
Y_targets=None,
n_epoch=100)
1536,
1,
bias=False,
activation=None,
name='Conv2d_7b_1x1')))
net = avg_pool_2d(net,
net.get_shape().as_list()[1:3],
strides=2,
padding='VALID',
name='AvgPool_1a_8x8')
net = flatten(net)
net = dropout(net, dropout_keep_prob)
loss = fully_connected(net, num_classes, activation='softmax')
network = zqtflearn.regression(loss,
optimizer='RMSprop',
loss='categorical_crossentropy',
learning_rate=0.0001)
model = zqtflearn.DNN(network,
checkpoint_path='inception_resnet_v2',
max_checkpoints=1,
tensorboard_verbose=2,
tensorboard_dir="./tflearn_logs/")
model.fit(X,
Y,
n_epoch=1000,
validation_set=0.1,
shuffle=True,
show_metric=True,
batch_size=32,
snapshot_step=2000,
snapshot_epoch=False,
n_words=10000,
valid_portion=0.1)
trainX, trainY = train
testX, testY = test
# Data preprocessing
# Sequence padding
trainX = pad_sequences(trainX, maxlen=100, value=0.)
testX = pad_sequences(testX, maxlen=100, value=0.)
# Converting labels to binary vectors
trainY = to_categorical(trainY)
testY = to_categorical(testY)
# Network building
net = zqtflearn.input_data([None, 100])
net = zqtflearn.embedding(net, input_dim=10000, output_dim=128)
net = zqtflearn.lstm(net, 128, dropout=0.8)
net = zqtflearn.fully_connected(net, 2, activation='softmax')
net = zqtflearn.regression(net,
optimizer='adam',
learning_rate=0.001,
loss='categorical_crossentropy')
# Training
model = zqtflearn.DNN(net, tensorboard_verbose=0)
model.fit(trainX,
trainY,
validation_set=(testX, testY),
show_metric=True,
batch_size=32)
import zqtflearn.datasets.mnist as mnist
X, Y, testX, testY = mnist.load_data(one_hot=True)
# Building the encoder
encoder = zqtflearn.input_data(shape=[None, 784])
encoder = zqtflearn.fully_connected(encoder, 256)
encoder = zqtflearn.fully_connected(encoder, 64)
# Building the decoder
decoder = zqtflearn.fully_connected(encoder, 256)
decoder = zqtflearn.fully_connected(decoder, 784, activation='sigmoid')
# Regression, with mean square error
net = zqtflearn.regression(decoder,
optimizer='adam',
learning_rate=0.001,
loss='mean_square',
metric=None)
# Training the auto encoder
model = zqtflearn.DNN(net, tensorboard_verbose=0)
model.fit(X,
X,
n_epoch=20,
validation_set=(testX, testX),
run_id="auto_encoder",
batch_size=256)
# Encoding X[0] for test
print("\nTest encoding of X[0]:")
# New model, re-using the same session, for weights sharing
dense1 = zqtflearn.fully_connected(input_layer,
64,
activation='tanh',
regularizer='L2',
weight_decay=0.001)
dropout1 = zqtflearn.dropout(dense1, 0.8)
dense2 = zqtflearn.fully_connected(dropout1,
64,
activation='tanh',
regularizer='L2',
weight_decay=0.001)
dropout2 = zqtflearn.dropout(dense2, 0.8)
softmax = zqtflearn.fully_connected(dropout2, 10, activation='softmax')
# Regression using SGD with learning rate decay and Top-3 accuracy
sgd = zqtflearn.SGD(learning_rate=0.1, lr_decay=0.96, decay_step=1000)
top_k = zqtflearn.metrics.Top_k(3)
net = zqtflearn.regression(softmax,
optimizer=sgd,
metric=top_k,
loss='categorical_crossentropy')
# Training
model = zqtflearn.DNN(net, tensorboard_verbose=0)
model.fit(X,
Y,
n_epoch=20,
validation_set=(testX, testY),
show_metric=True,
run_id="dense_model")
def model(self,
mode="train",
num_layers=1,
cell_size=32,
cell_type="BasicLSTMCell",
embedding_size=20,
learning_rate=0.0001,
tensorboard_verbose=0,
checkpoint_path=None):
'''
Build tensor specifying graph of operations for the seq2seq neural network model.
mode = string, either "train" or "predict"
cell_type = attribute of rnn_cell specifying which RNN cell type to use
cell_size = size for the hidden layer in the RNN cell
num_layers = number of RNN cell layers to use
Return TFLearn model instance. Use DNN model for this.
'''
assert mode in ["train", "predict"]
checkpoint_path = checkpoint_path or (
"%s%ss2s_checkpoint.tfl" %
(self.data_dir or "", "/" if self.data_dir else ""))
GO_VALUE = self.out_max_int + 1 # unique integer value used to trigger decoder outputs in the seq2seq RNN
network = zqtflearn.input_data(
shape=[None, self.in_seq_len + self.out_seq_len],
dtype=tf.int32,
name="XY")
encoder_inputs = tf.slice(network, [0, 0], [-1, self.in_seq_len],
name="enc_in") # get encoder inputs
encoder_inputs = tf.unstack(
encoder_inputs, axis=1
) # transform into list of self.in_seq_len elements, each [-1]
decoder_inputs = tf.slice(network, [0, self.in_seq_len],
[-1, self.out_seq_len],
name="dec_in") # get decoder inputs
decoder_inputs = tf.unstack(
decoder_inputs, axis=1
) # transform into list of self.out_seq_len elements, each [-1]
go_input = tf.multiply(
tf.ones_like(decoder_inputs[0], dtype=tf.int32), GO_VALUE
) # insert "GO" symbol as the first decoder input; drop the last decoder input
decoder_inputs = [
go_input
] + decoder_inputs[:self.out_seq_len -
1] # insert GO as first; drop last decoder input
feed_previous = not (mode == "train")
if self.verbose > 3:
print("feed_previous = %s" % str(feed_previous))
print("encoder inputs: %s" % str(encoder_inputs))
print("decoder inputs: %s" % str(decoder_inputs))
print("len decoder inputs: %s" % len(decoder_inputs))
self.n_input_symbols = self.in_max_int + 1 # default is integers from 0 to 9
self.n_output_symbols = self.out_max_int + 2 # extra "GO" symbol for decoder inputs
single_cell = getattr(rnn_cell, cell_type)(cell_size,
state_is_tuple=True)
if num_layers == 1:
cell = single_cell
else:
cell = rnn_cell.MultiRNNCell([single_cell] * num_layers)
if self.seq2seq_model == "embedding_rnn":
model_outputs, states = seq2seq.embedding_rnn_seq2seq(
encoder_inputs, # encoder_inputs: A list of 2D Tensors [batch_size, input_size].
decoder_inputs,
cell,
num_encoder_symbols=self.n_input_symbols,
num_decoder_symbols=self.n_output_symbols,
embedding_size=embedding_size,
feed_previous=feed_previous)
elif self.seq2seq_model == "embedding_attention":
model_outputs, states = seq2seq.embedding_attention_seq2seq(
encoder_inputs, # encoder_inputs: A list of 2D Tensors [batch_size, input_size].
decoder_inputs,
cell,
num_encoder_symbols=self.n_input_symbols,
num_decoder_symbols=self.n_output_symbols,
embedding_size=embedding_size,
num_heads=1,
initial_state_attention=False,
feed_previous=feed_previous)
else:
raise Exception('[TFLearnSeq2Seq] Unknown seq2seq model %s' %
self.seq2seq_model)
tf.add_to_collection(
tf.GraphKeys.LAYER_VARIABLES + '/' + "seq2seq_model",
model_outputs) # for TFLearn to know what to save and restore
# model_outputs: list of the same length as decoder_inputs of 2D Tensors with shape [batch_size x output_size] containing the generated outputs.
if self.verbose > 2: print("model outputs: %s" % model_outputs)
network = tf.stack(
model_outputs, axis=1
) # shape [-1, n_decoder_inputs (= self.out_seq_len), num_decoder_symbols]
if self.verbose > 2: print("packed model outputs: %s" % network)
if self.verbose > 3:
all_vars = tf.get_collection(tf.GraphKeys.VARIABLES)
print("all_vars = %s" % all_vars)
with tf.name_scope(
"TargetsData"
): # placeholder for target variable (i.e. trainY input)
targetY = tf.placeholder(shape=[None, self.out_seq_len],
dtype=tf.int32,
name="Y")
network = zqtflearn.regression(network,
placeholder=targetY,
optimizer='adam',
learning_rate=learning_rate,
loss=self.sequence_loss,
metric=self.accuracy,
name="Y")
model = zqtflearn.DNN(network,
tensorboard_verbose=tensorboard_verbose,
checkpoint_path=checkpoint_path)
return model
