Python keras.layers.Dense() Examples
The following are code examples for showing how to use keras.layers.Dense(). They are from open source Python projects. You can vote up the examples you like or vote down the ones you don't like.
Example 1
| Project: speed_estimation Author: NeilNie File: simple_conv.py MIT License | 13 votes |
|
def commaai_model(self):
model = Sequential()
model.add(Lambda(lambda x: x / 127.5 - 1., input_shape=(configs.IMG_HEIGHT, configs.IMG_WIDTH, 3), output_shape=(configs.IMG_HEIGHT, configs.IMG_WIDTH, 3)))
model.add(Conv2D(16, (8, 8), strides=4, padding="same"))
model.add(ELU())
model.add(Conv2D(32, (5, 5), strides=2, padding="same"))
model.add(ELU())
model.add(Conv2D(64, (5, 5), strides=2, padding="same"))
model.add(Flatten())
model.add(Dropout(.2))
model.add(ELU())
model.add(Dense(512))
model.add(Dropout(.5))
model.add(ELU())
model.add(Dense(1))
sgd = SGD(lr=0.00001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(optimizer=sgd, loss='mean_squared_error')
# print('steering model is created and compiled...')
return model
Example 2
| Project: keras-anomaly-detection Author: chen0040 File: recurrent.py MIT License | 9 votes |
|
def create_model(time_window_size, metric):
model = Sequential()
model.add(Conv1D(filters=256, kernel_size=5, padding='same', activation='relu',
input_shape=(time_window_size, 1)))
model.add(MaxPooling1D(pool_size=4))
model.add(LSTM(64))
model.add(Dense(units=time_window_size, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
# model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
# model.compile(optimizer="sgd", loss="mse", metrics=[metric])
print(model.summary())
return model
Example 3
| Project: Kaggle-Statoil-Challenge Author: adodd202 File: VGG_OutputGen.py MIT License | 7 votes |
|
def getVGGModel():
input_2 = Input(shape=[1], name="angle")
angle_layer = Dense(1, )(input_2)
base_model = VGG16(weights='imagenet', include_top=False,
input_shape=X_train.shape[1:], classes=1)
x = base_model.get_layer('block5_pool').output
x = GlobalMaxPooling2D()(x)
merge_one = concatenate([x, angle_layer])
merge_one = Dense(512, activation='relu', name='fc2')(merge_one)
merge_one = Dropout(0.3)(merge_one)
merge_one = Dense(512, activation='relu', name='fc3')(merge_one)
merge_one = Dropout(0.3)(merge_one)
predictions = Dense(1, activation='sigmoid')(merge_one)
model = Model(inputs=[base_model.input, input_2], outputs=predictions)
# adam = Adam(lr=1e-3, epsilon = 1e-8, beta_1 = .9, beta_2 = .999)
# model.compile(loss='binary_crossentropy',
# optimizer=adam,
# metrics=['accuracy'])
return model
Example 4
| Project: oslodatascience-rl Author: Froskekongen File: havakv_atari.py MIT License | 7 votes |
|
def deepMindAtariNet(nbClasses, inputShape, includeTop=True):
'''Set up the 3 conv layer keras model.
classes: Number of outputs.
inputShape: The input shape without the batch size.
includeTop: If you only want the whole net, or just the convolutions.
'''
inp = Input(shape=inputShape)
x = Conv2D(32, 8, 8, subsample=(4, 4), activation='relu', border_mode='same', name='conv1')(inp)
x = Conv2D(64, 4, 4, subsample=(2, 2), activation='relu', border_mode='same', name='conv2')(x)
x = Conv2D(64, 3, 3, activation='relu', border_mode='same', name='conv3')(x)
if includeTop:
x = Flatten(name='flatten')(x)
x = Dense(512, activation='relu', name='dense1')(x)
out = Dense(nbClasses, activation='softmax', name='output')(x)
else:
out = x
model = Model(inp, out)
return model
Example 5
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 7 votes |
|
def weather_l2(hidden_nums=100,l2=0.01):
input_img = Input(shape=(37,))
hn = Dense(hidden_nums, activation='relu')(input_img)
hn = Dense(hidden_nums, activation='relu',
kernel_regularizer=regularizers.l2(l2))(hn)
out_u = Dense(37, activation='sigmoid',
name='ae_part')(hn)
out_sig = Dense(37, activation='linear',
name='pred_part')(hn)
out_both = concatenate([out_u, out_sig], axis=1, name = 'concatenate')
#weather_model = Model(input_img, outputs=[out_ae, out_pred])
mve_model = Model(input_img, outputs=[out_both])
mve_model.compile(optimizer='adam', loss=mve_loss, loss_weights=[1.])
return mve_model
Example 6
| Project: Anamoly-Detection Author: msmsk05 File: gaal_base.py BSD 2-Clause "Simplified" License | 7 votes |
|
def create_generator(latent_size): # pragma: no cover
"""Create the generator of the GAN for a given latent size.
Parameters
----------
latent_size : int
The size of the latent space of the generator
Returns
-------
D : Keras model() object
Returns a model() object.
"""
gen = Sequential()
gen.add(Dense(latent_size, input_dim=latent_size, activation='relu',
kernel_initializer=keras.initializers.Identity(
gain=1.0)))
gen.add(Dense(latent_size, activation='relu',
kernel_initializer=keras.initializers.Identity(
gain=1.0)))
latent = Input(shape=(latent_size,))
fake_data = gen(latent)
return Model(latent, fake_data)
Example 7
| Project: VisualNN Author: angelhunt File: test_views.py GNU General Public License v3.0 | 6 votes |
|
def test_keras_export(self):
tests = open(os.path.join(settings.BASE_DIR, 'tests', 'unit', 'keras_app',
'keras_export_test.json'), 'r')
response = json.load(tests)
tests.close()
net = yaml.safe_load(json.dumps(response['net']))
net = {'l0': net['Input2'], 'l1': net['InnerProduct']}
net['l0']['connection']['output'].append('l1')
# Test 1
inp = data(net['l0'], '', 'l0')['l0']
temp = dense(net['l1'], [inp], 'l1')
model = Model(inp, temp['l1'])
self.assertEqual(model.layers[2].__class__.__name__, 'Dense')
# Test 2
net['l1']['params']['weight_filler'] = 'glorot_normal'
net['l1']['params']['bias_filler'] = 'glorot_normal'
inp = data(net['l0'], '', 'l0')['l0']
temp = dense(net['l1'], [inp], 'l1')
model = Model(inp, temp['l1'])
self.assertEqual(model.layers[2].__class__.__name__, 'Dense')
Example 8
| Project: oslodatascience-rl Author: Froskekongen File: erlenda_pong_parallel.py MIT License | 6 votes |
|
def buildmodel(opt):
print("Now we build the model")
model = Sequential()
model.add(Convolution2D(32, 8, 8, subsample=(4,4), border_mode='same',input_shape=(80,80,1)))
model.add(Activation('relu'))
model.add(Convolution2D(64, 4, 4, subsample=(2,2), border_mode='same'))
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3, subsample=(1,1), border_mode='same'))
model.add(Activation('relu'))
model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dense(1))
model.compile(loss='binary_crossentropy',optimizer=opt)
print("We finish building the model")
return model
Example 9
| Project: oslodatascience-rl Author: Froskekongen File: erlenda_pong_parallel.py MIT License | 6 votes |
|
def get_dense_model():
"""Make keras model"""
learning_rate=1e-4
inp = Input(shape=(80*80,))
h = Dense(200, activation='relu')(inp)
out = Dense(1, activation='sigmoid')(h)
model = Model(inp, out)
optim = RMSprop(learning_rate)
model.compile(optim, 'binary_crossentropy')
try:
model.load_weights('mod_weights_binary.h5')
print('weights loaded')
except:
pass
return model
Example 10
| Project: Image-Caption-Generator Author: dabasajay File: model.py MIT License | 6 votes |
|
def RNNModel(vocab_size, max_len, rnnConfig, model_type): embedding_size = rnnConfig['embedding_size'] if model_type == 'inceptionv3': # InceptionV3 outputs a 2048 dimensional vector for each image, which we'll feed to RNN Model image_input = Input(shape=(2048,)) elif model_type == 'vgg16': # VGG16 outputs a 4096 dimensional vector for each image, which we'll feed to RNN Model image_input = Input(shape=(4096,)) image_model_1 = Dropout(rnnConfig['dropout'])(image_input) image_model = Dense(embedding_size, activation='relu')(image_model_1) caption_input = Input(shape=(max_len,)) # mask_zero: We zero pad inputs to the same length, the zero mask ignores those inputs. E.g. it is an efficiency. caption_model_1 = Embedding(vocab_size, embedding_size, mask_zero=True)(caption_input) caption_model_2 = Dropout(rnnConfig['dropout'])(caption_model_1) caption_model = LSTM(rnnConfig['LSTM_units'])(caption_model_2) # Merging the models and creating a softmax classifier final_model_1 = concatenate([image_model, caption_model]) final_model_2 = Dense(rnnConfig['dense_units'], activation='relu')(final_model_1) final_model = Dense(vocab_size, activation='softmax')(final_model_2) model = Model(inputs=[image_input, caption_input], outputs=final_model) model.compile(loss='categorical_crossentropy', optimizer='adam') return model
Example 11
| Project: keras-anomaly-detection Author: chen0040 File: feedforward.py MIT License | 6 votes |
|
def create_model(self, input_dim):
encoding_dim = 14
input_layer = Input(shape=(input_dim,))
encoder = Dense(encoding_dim, activation="tanh",
activity_regularizer=regularizers.l1(10e-5))(input_layer)
encoder = Dense(encoding_dim // 2, activation="relu")(encoder)
decoder = Dense(encoding_dim // 2, activation='tanh')(encoder)
decoder = Dense(input_dim, activation='relu')(decoder)
model = Model(inputs=input_layer, outputs=decoder)
model.compile(optimizer='adam',
loss='mean_squared_error',
metrics=['accuracy'])
return model
Example 12
| Project: smach_based_introspection_framework Author: birlrobotics File: anomaly_model_generation.py BSD 3-Clause "New" or "Revised" License | 6 votes |
|
def squeeze_excite_block(input):
''' Create a squeeze-excite block
Args:
input: input tensor
filters: number of output filters
k: width factor
Returns: a keras tensor
'''
filters = input._keras_shape[-1] # channel_axis = -1 for TF
se = GlobalAveragePooling1D()(input)
se = Reshape((1, filters))(se)
se = Dense(filters // 16, activation='relu', kernel_initializer='he_normal', use_bias=False)(se)
se = Dense(filters, activation='sigmoid', kernel_initializer='he_normal', use_bias=False)(se)
se = multiply([input, se])
return se
Example 13
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 6 votes |
|
def CausalCNN(n_filters, lr, decay, loss,
seq_len, input_features,
strides_len, kernel_size,
dilation_rates):
inputs = Input(shape=(seq_len, input_features), name='input_layer')
x=inputs
for dilation_rate in dilation_rates:
x = Conv1D(filters=n_filters,
kernel_size=kernel_size,
padding='causal',
dilation_rate=dilation_rate,
activation='linear')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
#x = Dense(7, activation='relu', name='dense_layer')(x)
outputs = Dense(3, activation='sigmoid', name='output_layer')(x)
causalcnn = Model(inputs, outputs=[outputs])
return causalcnn
Example 14
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 6 votes |
|
def weather_ae(layers, lr, decay, loss,
input_len, input_features):
inputs = Input(shape=(input_len, input_features), name='input_layer')
for i, hidden_nums in enumerate(layers):
if i==0:
hn = Dense(hidden_nums, activation='relu')(inputs)
else:
hn = Dense(hidden_nums, activation='relu')(hn)
outputs = Dense(3, activation='sigmoid', name='output_layer')(hn)
weather_model = Model(inputs, outputs=[outputs])
return weather_model
Example 15
| Project: ANN Author: waynezv File: ANN_v0.1.py MIT License | 6 votes |
|
def train(in_dim, out_dim, X_train, Y_train, X_test, Y_test):
model = Sequential()
model.add(Dense(100000, input_dim = in_dim, init='uniform'))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(100000, init='uniform'))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(out_dim, init='uniform'))
model.add(Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd',\
metrics=['accuracy'])
hist = model.fit(X_train, Y_train, nb_epoch=5, batch_size=32,\
validation_split=0.1, shuffle=True)
print(hist.history)
loss_and_metrics = model.evaluate(X_test, Y_test, batch_size=32)
classes = model.predict_classes(X_test, batch_size=32)
proba = model.predict_proba(X_test, batch_size=32)
Example 16
| Project: phoneticSimilarity Author: ronggong File: models_RNN.py GNU Affero General Public License v3.0 | 6 votes |
|
def embedding_RNN_1_lstm_1_dense(input_shape):
device = device_lib.list_local_devices()[0].device_type
input = Input(batch_shape=input_shape)
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=False))(input)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(input)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x, input
Example 17
| Project: phoneticSimilarity Author: ronggong File: models_RNN.py GNU Affero General Public License v3.0 | 6 votes |
|
def embedding_RNN_2_lstm_1_dense(input_shape):
device = device_lib.list_local_devices()[0].device_type
input = Input(batch_shape=input_shape)
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=True))(input)
x = Bidirectional(LSTM(units=32, return_sequences=False))(x)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(input)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x, input
Example 18
| Project: phoneticSimilarity Author: ronggong File: models_RNN.py GNU Affero General Public License v3.0 | 6 votes |
|
def embedding_RNN_2_lstm_2_dense(input_shape):
device = device_lib.list_local_devices()[0].device_type
input = Input(batch_shape=input_shape)
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=True))(input)
x = Bidirectional(LSTM(units=32, return_sequences=False))(x)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(input)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x, input
Example 19
| Project: phoneticSimilarity Author: ronggong File: models_RNN.py GNU Affero General Public License v3.0 | 6 votes |
|
def embedding_RNN_3_lstm_1_dense(input_shape):
device = device_lib.list_local_devices()[0].device_type
input = Input(batch_shape=input_shape)
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=True))(input)
x = Bidirectional(LSTM(units=32, return_sequences=True))(x)
x = Bidirectional(LSTM(units=32, return_sequences=False))(x)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(input)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(x)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x, input
Example 20
| Project: phoneticSimilarity Author: ronggong File: models_RNN.py GNU Affero General Public License v3.0 | 6 votes |
|
def embedding_RNN_3_lstm_2_dense(input_shape):
device = device_lib.list_local_devices()[0].device_type
input = Input(batch_shape=input_shape)
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=True))(input)
x = Bidirectional(LSTM(units=32, return_sequences=True))(x)
x = Bidirectional(LSTM(units=32, return_sequences=False))(x)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(input)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(x)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x, input
Example 21
| Project: mtrl-auto-uav Author: brunapearson File: mtrl_network.py MIT License | 5 votes |
|
def create_model():
#Create the convolutional stacks
input_img = Input(shape=(224,224,3))
x = Conv2D(16, kernel_size=3, activation='relu')(input_img)
x = MaxPooling2D(pool_size=(2,2))(x)
x = Conv2D(32, kernel_size=3, activation='relu')(x)
x = MaxPooling2D(pool_size=(2,2))(x)
x = Conv2D(64, kernel_size=3, activation='relu')(x)
x = MaxPooling2D(pool_size=(2,2))(x)
x = Flatten()(x)
x = Dense(500, activation='relu')(x)
x = Dropout(0.20)(x)
x = Dense(100, activation='relu')(x)
x = Dense(20, activation='relu')(x)
n = Conv2D(16, kernel_size=3, activation='relu')(input_img)
n = MaxPooling2D(pool_size=(2,2))(n)
n = Conv2D(32, kernel_size=3, activation='relu')(n)
n = MaxPooling2D(pool_size=(2,2))(n)
n = Conv2D(64, kernel_size=3, activation='relu')(n)
n = MaxPooling2D(pool_size=(2,2))(n)
n = Flatten()(n)
n = Dense(500, activation='relu')(n)
#n = Dropout(0.50)(n)
n = Dense(100, activation='relu')(n)
n = Dense(20, activation='relu')(n)
#output
output_x = Dense(1, activation='linear', name='input_x')(n)
output_y = Dense(1, activation='linear', name='input_y')(n)
output_z = Dense(1, activation='linear', name='input_z')(n)
output_qw = Dense(1, activation='linear', name='input_qw')(x)
output_qx = Dense(1, activation='linear', name='input_qx')(x)
output_qy = Dense(1, activation='linear', name='input_qy')(x)
output_qz = Dense(1, activation='linear', name='input_qz')(x)
model = Model(inputs=input_img, outputs=[output_x,output_y,output_z,output_qw,output_qx,output_qy,output_qz])
return model
Example 22
| Project: sklearn2docker Author: KhaledSharif File: keras_classifier_test.py GNU Lesser General Public License v3.0 | 5 votes |
|
def create_binary_classification_model():
from keras.models import Sequential
from keras.layers import Dense, Dropout
model = Sequential()
model.add(Dense(64, input_shape=(30,), activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy', optimizer='adam')
return model
Example 23
| Project: sklearn2docker Author: KhaledSharif File: keras_classifier_test.py GNU Lesser General Public License v3.0 | 5 votes |
|
def create_categorical_classification_model():
from keras.models import Sequential
from keras.layers import Dense, Dropout
model = Sequential()
model.add(Dense(64, input_shape=(30,), activation='relu'))
model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(3, activation='sigmoid'))
model.compile(loss='categorical_crossentropy', optimizer='adam')
return model
Example 24
| Project: VisualNN Author: angelhunt File: layers_export.py GNU General Public License v3.0 | 5 votes |
|
def dense(layer, layer_in, layerId, tensor=True):
out = {}
if (len(layer['shape']['input']) > 1):
out[layerId + 'Flatten'] = Flatten()(*layer_in)
layer_in = [out[layerId + 'Flatten']]
units = layer['params']['num_output']
if (layer['params']['weight_filler'] in fillerMap):
kernel_initializer = fillerMap[layer['params']['weight_filler']]
else:
kernel_initializer = layer['params']['weight_filler']
if (layer['params']['bias_filler'] in fillerMap):
bias_initializer = fillerMap[layer['params']['bias_filler']]
else:
bias_initializer = layer['params']['bias_filler']
# safety checks to avoid runtime errors
kernel_regularizer = None
bias_regularizer = None
activity_regularizer = None
kernel_constraint = None
bias_constraint = None
if 'kernel_regularizer' in layer['params']:
kernel_regularizer = regularizerMap[layer['params']['kernel_regularizer']]
if 'bias_regularizer' in layer['params']:
bias_regularizer = regularizerMap[layer['params']['bias_regularizer']]
if 'activity_regularizer' in layer['params']:
activity_regularizer = regularizerMap[layer['params']
['activity_regularizer']]
if 'kernel_constraint' in layer['params']:
kernel_constraint = constraintMap[layer['params']['kernel_constraint']]
if 'bias_constraint' in layer['params']:
bias_constraint = constraintMap[layer['params']['bias_constraint']]
use_bias = layer['params']['use_bias']
out[layerId] = Dense(units=units, kernel_initializer=kernel_initializer,
kernel_regularizer=kernel_regularizer, bias_regularizer=bias_regularizer,
activity_regularizer=activity_regularizer, bias_constraint=bias_constraint,
kernel_constraint=kernel_constraint, use_bias=use_bias,
bias_initializer=bias_initializer)
if tensor:
out[layerId] = out[layerId](*layer_in)
return out
Example 25
| Project: VisualNN Author: angelhunt File: test_views.py GNU General Public License v3.0 | 5 votes |
|
def test_keras_import(self):
model = Sequential()
model.add(Dense(100, kernel_regularizer=regularizers.l2(0.01), bias_regularizer=regularizers.l2(0.01),
activity_regularizer=regularizers.l2(0.01), kernel_constraint='max_norm',
bias_constraint='max_norm', activation='relu', input_shape=(16,)))
model.build()
self.keras_param_test(model, 1, 3)
Example 26
| Project: Kaggle-Statoil-Challenge Author: adodd202 File: capsulenet.py MIT License | 5 votes |
|
def CapsNet(input_shape, n_class, num_routing):
"""
A Capsule Network on MNIST.
:param input_shape: data shape, 3d, [width, height, channels]
:param n_class: number of classes
:param num_routing: number of routing iterations
:return: Two Keras Models, the first one used for training, and the second one for evaluation.
`eval_model` can also be used for training.
"""
x = layers.Input(shape=input_shape)
# Layer 1: Just a conventional Conv2D layer
conv1 = layers.Conv2D(filters=256, kernel_size=9, strides=1, padding='valid', activation='relu', name='conv1')(x)
# Layer 2: Conv2D layer with `squash` activation, then reshape to [None, num_capsule, dim_capsule]
primarycaps = PrimaryCap(conv1, dim_capsule=8, n_channels=32, kernel_size=9, strides=2, padding='valid')
# Layer 3: Capsule layer. Routing algorithm works here.
digitcaps = CapsuleLayer(num_capsule=n_class, dim_capsule=16, num_routing=num_routing,
name='digitcaps')(primarycaps)
# Layer 4: This is an auxiliary layer to replace each capsule with its length. Just to match the true label's shape.
# If using tensorflow, this will not be necessary. :)
out_caps = Length(name='capsnet')(digitcaps)
# Decoder network.
y = layers.Input(shape=(n_class,))
masked_by_y = Mask()([digitcaps, y]) # The true label is used to mask the output of capsule layer. For training
masked = Mask()(digitcaps) # Mask using the capsule with maximal length. For prediction
# Shared Decoder model in training and prediction
decoder = models.Sequential(name='decoder')
decoder.add(layers.Dense(512, activation='relu', input_dim=16*n_class))
decoder.add(layers.Dense(1024, activation='relu'))
decoder.add(layers.Dense(np.prod(input_shape), activation='sigmoid'))
decoder.add(layers.Reshape(target_shape=input_shape, name='out_recon'))
# Models for training and evaluation (prediction)
train_model = models.Model([x, y], [out_caps, decoder(masked_by_y)])
eval_model = models.Model(x, [out_caps, decoder(masked)])
return train_model, eval_model
Example 27
| Project: Kaggle-Statoil-Challenge Author: adodd202 File: VGG16_BottleNeck.py MIT License | 5 votes |
|
def getVGGModel():
input_2 = Input(shape=[1], name="angle")
angle_layer = Dense(1, )(input_2)
base_model = VGG16(weights='imagenet', include_top=False,
input_shape=X_train.shape[1:], classes=1)
x = base_model.get_layer('block5_pool').output
x = GlobalMaxPooling2D()(x)
merge_one = concatenate([x, angle_layer])
merge_one = Dense(512, activation='relu', name='fc2')(merge_one)
merge_one = Dropout(0.3)(merge_one)
merge_one = Dense(512, activation='relu', name='fc3')(merge_one)
merge_one = Dropout(0.3)(merge_one)
predictions = Dense(1, activation='sigmoid')(merge_one)
model = Model(input=[base_model.input, input_2], output=predictions)
adam = Adam(lr=1e-3, epsilon = 1e-8, beta_1 = .9, beta_2 = .999)
model.compile(loss='binary_crossentropy',
optimizer=adam,
metrics=['accuracy'])
return model
################
#Using K-fold Cross Validation with Data Augmentation.
Example 28
| Project: MODS_ConvNet Author: santiagolopezg File: hipster_net.py MIT License | 5 votes |
|
def cifar():
# Determine proper input shape
K.set_image_dim_ordering('th')
input_shape = (1, 256, 192)
img_input = Input(shape=input_shape)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='conv1_1')(img_input)
x = Convolution2D(64, 3, 3, activation='relu', border_mode='same', name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='conv2_1')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='conv2_2')(x)
x = Convolution2D(128, 3, 3, activation='relu', border_mode='same', name='conv2_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='conv3_1')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='conv3_2')(x)
x = Convolution2D(256, 3, 3, activation='relu', border_mode='same', name='conv3_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='conv4_1')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='conv4_2')(x)
x = Convolution2D(512, 3, 3, activation='relu', border_mode='same', name='conv4_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4')(x)
x = Flatten(name='flatten')(x)
x = Dense(1000, activation='relu', name='fc1')(x)
x = Dense(1000, activation='relu', name='fc2')(x)
x = Dense(2, activation='softmax', name='pred')(x)
# Create model.
model = Model(img_input, x)
#weights='MODS_keras_weights_3_he_normal_0.5_rmsprop_24.h5'
#model.load_weights(weights)
return model
Example 29
| Project: neural-fingerprinting Author: StephanZheng File: test_utils_keras.py BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def setUp(self):
from keras.models import Sequential
from keras.layers import Dense, Activation
import tensorflow as tf
def dummy_model():
input_shape = (100,)
return Sequential([Dense(20, name='l1',
input_shape=input_shape),
Dense(10, name='l2'),
Activation('softmax', name='softmax')])
self.sess = tf.Session()
self.sess.as_default()
self.model = dummy_model()
Example 30
| Project: oslodatascience-rl Author: Froskekongen File: havakv_atari_multi.py MIT License | 5 votes |
|
def deepMindAtariNet(nbClasses, inputShape, includeTop=True):
'''Set up the 3 conv layer keras model.
classes: Number of outputs.
inputShape: The input shape without the batch size.
includeTop: If you only want the whole net, or just the convolutions.
'''
inp = Input(shape=inputShape)
x = Conv2D(32, 8, 8, subsample=(4, 4), activation='relu', border_mode='same', name='conv1')(inp)
x = Conv2D(64, 4, 4, subsample=(2, 2), activation='relu', border_mode='same', name='conv2')(x)
x = Conv2D(64, 3, 3, activation='relu', border_mode='same', name='conv3')(x)
if includeTop:
x = Flatten(name='flatten')(x)
x = Dense(512, activation='relu', name='dense1')(x)
out = Dense(nbClasses, activation='softmax', name='output')(x)
else:
out = x
model = Model(inp, out)
return model
Example 31
| Project: oslodatascience-rl Author: Froskekongen File: havakv_atari_multi.py MIT License | 5 votes |
|
def setupModel(self):
'''Setup models:
self.actionModel is the action predictions.
self.valueModel is the prediction of the value function.
self.model is the model with both outputs
'''
inputShape = (self.D, self.D, self.nbImgInState)
model = self.deepMindAtariNet(self.nbActionClasses, inputShape, includeTop=False)
inp = Input(shape=inputShape)
x = model(inp)
x = Flatten()(x)
x = Dense(512, activation='relu', name='dense1')(x)
action = Dense(self.nbActionClasses, activation='softmax', name='action')(x)
self.actionModel = Model(inp, action)
# Should we compile model?
value = Dense(1, activation='linear', name='value')(x)
self.valueModel = Model(inp, value)
# Should we compile model?
self.model = Model(inp, [action, value])
actionAndEntropyLoss = makeActionAndEntropyLossA3C(self.entropyBeta)
loss = {'action': actionAndEntropyLoss, 'value': 'mse'}
loss_weights = {'action': 1, 'value': self.mseBeta}
optim = RMSprop(self.learningRate, self.decayRate)
self.model.compile(optim, loss) # Need to make it possible to set other optimizers
if self.resume:
self.model.load_weights(self.modelFileName)
return
Example 32
| Project: oslodatascience-rl Author: Froskekongen File: havakv_atari_multi.py MIT License | 5 votes |
|
def setupModel(self):
"""Make keras model"""
if self.resume:
self.model = load_model(self.modelFileName)
else:
inp = Input(shape=(self.D,))
h = Dense(self.H, activation='relu')(inp)
out = Dense(1, activation='sigmoid')(h)
self.model = Model(inp, out)
optim = RMSprop(self.learning_rate, self.decay_rate)
self.model.compile(optim, 'binary_crossentropy')
# @staticmethod
# def _preprocess_image(I):
# '''Preprocess 210x160x3 uint8 frame into 6400 (80x80) 1D float vector'''
# I = I[35:195] # crop
# I = I[::2,::2,0] # downsample by factor of 2
# I[I == 144] = 0 # erase background (background type 1)
# I[I == 109] = 0 # erase background (background type 2)
# I[I != 0] = 1 # everything else (paddles, ball) just set to 1
# return I.astype(np.float).ravel()
# def preprocess(self, observation):
# '''Proprocess observation. And store in states list'''
# cur_x = self._preprocess_image(observation)
# x = cur_x - self.prev_x if self.prev_x is not None else np.zeros(self.D)
# self.prev_x = cur_x
# x = x.reshape((1, -1))
# self.states.append(x)
Example 33
| Project: oslodatascience-rl Author: Froskekongen File: havakv_atari.py MIT License | 5 votes |
|
def setupModel(self):
'''Setup models:
self.actionModel is the action predictions.
self.valueModel is the prediction of the value function.
self.model is the model with both outputs
'''
if self.resume:
self.model = load_model(self.modelFileName)
# Need the other models as well...
return
inputShape = (self.D, self.D, self.nbImgInState)
model = self.deepMindAtariNet(self.nbClasses, inputShape, includeTop=False)
inp = Input(shape=inputShape)
x = model(inp)
x = Flatten()(x)
x = Dense(512, activation='relu', name='dense1')(x)
action = Dense(self.nbClasses, activation='softmax', name='action')(x)
self.actionModel = Model(inp, action)
# Should we compile model?
value = Dense(1, activation='linear', name='value')(x)
self.valueModel = Model(inp, value)
# Should we compile model?
self.model = Model(inp, [action, value])
# loss = {'action': 'categorical_crossentropy', 'value': 'mse'}
# loss = {'action': categoricalCrossentropyWithWeights, 'value': 'mse'}
actionAndEntropyLoss = makeActionAndEntropyLossA3C(self.entropyBeta)
loss = {'action': actionAndEntropyLoss, 'value': 'mse'}
loss_weights = {'action': 1, 'value': self.mseBeta}
optim = RMSprop(self.learningRate, self.decayRate)
self.model.compile(optim, loss) # Need to make it possible to set other optimizers
Example 34
| Project: oslodatascience-rl Author: Froskekongen File: havakv_a2c.py MIT License | 5 votes |
|
def setupModel(self):
'''Setup models:
self.actionModel is the action predictions.
self.valueModel is the prediction of the value function V.
self.model is the model with both outputs
'''
inputShape = (self.D, self.D, self.nbImgInState)
inp = Input(shape=inputShape)
x = Conv2D(32, 8, 8, subsample=(4, 4), activation='relu', border_mode='same', name='conv1')(inp)
x = Conv2D(64, 4, 4, subsample=(2, 2), activation='relu', border_mode='same', name='conv2')(x)
x = Conv2D(64, 3, 3, activation='relu', border_mode='same', name='conv3')(x)
x = Flatten(name='flatten')(x)
x = Dense(512, activation='relu', name='dense1')(x)
action = Dense(self.nbActionClasses, activation='softmax', name='action')(x)
self.actionModel = Model(inp, action)
# Should we compile model?
value = Dense(1, activation='linear', name='value')(x)
self.valueModel = Model(inp, value)
# Should we compile model?
self.model = Model(inp, [action, value])
actionAndEntropyLoss = makeActionAndEntropyLossA3C(self.entropyBeta)
loss = {'action': actionAndEntropyLoss, 'value': 'mse'}
loss_weights = {'action': 1, 'value': self.mseBeta}
optim = RMSprop(self.learningRate, self.decayRate)
self.model.compile(optim, loss)
if self.resume:
self.model.load_weights(self.modelFileName)
return
Example 35
| Project: oslodatascience-rl Author: Froskekongen File: erlenda_pong_parallel.py MIT License | 5 votes |
|
def create_perc_model(input_dim,hidden_dim):
inp=Input(shape=(80,80,1), dtype='float32', name='main_input')
dd=Flatten()(inp)
dd=Dense(hidden_dim,activation='relu')(dd)
out=Dense(1,activation='sigmoid')(dd)
return inp,out
Example 36
| Project: oslodatascience-rl Author: Froskekongen File: erlenda_pong_parallel.py MIT License | 5 votes |
|
def create_conv_model(input_dim):
inp=Input(shape=(80,80,1), dtype='float32', name='main_input')
dd=Convolution2D(32,4,4,border_mode='same',activation='relu')(inp)
dd=Convolution2D(32,4,4,border_mode='same',activation='relu')(dd)
dd=Flatten()(dd)
out=Dense(1,activation='sigmoid')(dd)
return inp,out
Example 37
| Project: oslodatascience-rl Author: Froskekongen File: pogn_parallel.py MIT License | 5 votes |
|
def setupModel(self):
inp = Input(shape=(self.input_dimensions,))
h = Dense(self.num_hidden_layer_neurons, activation='relu')(inp)
out = Dense(1, activation='sigmoid')(h)
self.model = Model(inp, out)
optim = RMSprop(self.learning_rate, self.decay_rate)
self.model.compile(optim, 'binary_crossentropy')
#self.model._make_predict_function()
#self.graph = tf.get_default_graph()
Example 38
| Project: oslodatascience-rl Author: Froskekongen File: havakv_pongDense.py MIT License | 5 votes |
|
def get_dense_model():
"""Make keras model"""
if resume:
return load_model(model_file_name)
inp = Input(shape=(D,))
h = Dense(H, activation='relu')(inp)
out = Dense(1, activation='sigmoid')(h)
model = Model(inp, out)
optim = RMSprop(learning_rate, decay_rate)
model.compile(optim, 'binary_crossentropy')
return model
Example 39
| Project: Image-Caption-Generator Author: dabasajay File: model.py MIT License | 5 votes |
|
def AlternativeRNNModel(vocab_size, max_len, rnnConfig, model_type): embedding_size = rnnConfig['embedding_size'] if model_type == 'inceptionv3': # InceptionV3 outputs a 2048 dimensional vector for each image, which we'll feed to RNN Model image_input = Input(shape=(2048,)) elif model_type == 'vgg16': # VGG16 outputs a 4096 dimensional vector for each image, which we'll feed to RNN Model image_input = Input(shape=(4096,)) image_model_1 = Dense(embedding_size, activation='relu')(image_input) image_model = RepeatVector(max_len)(image_model_1) caption_input = Input(shape=(max_len,)) # mask_zero: We zero pad inputs to the same length, the zero mask ignores those inputs. E.g. it is an efficiency. caption_model_1 = Embedding(vocab_size, embedding_size, mask_zero=True)(caption_input) # Since we are going to predict the next word using the previous words # (length of previous words changes with every iteration over the caption), we have to set return_sequences = True. caption_model_2 = LSTM(rnnConfig['LSTM_units'], return_sequences=True)(caption_model_1) # caption_model = TimeDistributed(Dense(embedding_size, activation='relu'))(caption_model_2) caption_model = TimeDistributed(Dense(embedding_size))(caption_model_2) # Merging the models and creating a softmax classifier final_model_1 = concatenate([image_model, caption_model]) # final_model_2 = LSTM(rnnConfig['LSTM_units'], return_sequences=False)(final_model_1) final_model_2 = Bidirectional(LSTM(rnnConfig['LSTM_units'], return_sequences=False))(final_model_1) # final_model_3 = Dense(rnnConfig['dense_units'], activation='relu')(final_model_2) # final_model = Dense(vocab_size, activation='softmax')(final_model_3) final_model = Dense(vocab_size, activation='softmax')(final_model_2) model = Model(inputs=[image_input, caption_input], outputs=final_model) model.compile(loss='categorical_crossentropy', optimizer='adam') # model.compile(loss='categorical_crossentropy', optimizer='rmsprop') return model
Example 40
| Project: deep-learning-note Author: wdxtub File: 3_price_prediction.py MIT License | 5 votes |
|
def build_model():
model = models.Sequential()
model.add(layers.Dense(64, activation='relu', input_shape=(train_data.shape[1], )))
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(1))
model.compile(optimizer='rmsprop', loss='mse', metrics=['mae'])
return model
Example 41
| Project: keras-anomaly-detection Author: chen0040 File: convolutional.py MIT License | 5 votes |
|
def create_model(time_window_size, metric):
model = Sequential()
model.add(Conv1D(filters=256, kernel_size=5, padding='same', activation='relu',
input_shape=(time_window_size, 1)))
model.add(GlobalMaxPool1D())
model.add(Dense(units=time_window_size, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
print(model.summary())
return model
Example 42
| Project: keras-anomaly-detection Author: chen0040 File: recurrent.py MIT License | 5 votes |
|
def create_model(time_window_size, metric):
model = Sequential()
model.add(LSTM(units=128, input_shape=(time_window_size, 1), return_sequences=False))
model.add(Dense(units=time_window_size, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
print(model.summary())
return model
Example 43
| Project: keras-anomaly-detection Author: chen0040 File: recurrent.py MIT License | 5 votes |
|
def create_model(time_window_size, metric):
model = Sequential()
model.add(Bidirectional(LSTM(units=64, dropout=0.2, recurrent_dropout=0.2), input_shape=(time_window_size, 1)))
model.add(Dense(units=time_window_size, activation='linear'))
model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
# model.compile(optimizer='adam', loss='mean_squared_error', metrics=[metric])
# model.compile(optimizer="sgd", loss="mse", metrics=[metric])
print(model.summary())
return model
Example 44
| Project: smach_based_introspection_framework Author: birlrobotics File: anomaly_model_generation.py BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def generate_model_3():
ip = Input(shape=(MAX_NB_VARIABLES, MAX_TIMESTEPS))
x = Masking()(ip)
x = LSTM(8)(x)
x = Dropout(0.8)(x)
y = Permute((2, 1))(ip)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
#y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
#y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(NB_CLASS, activation='softmax')(x)
model = Model(ip, out)
model.summary()
# add load model code here to fine-tune
return model
Example 45
| Project: smach_based_introspection_framework Author: birlrobotics File: anomaly_model_generation.py BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def generate_model_4():
ip = Input(shape=(MAX_NB_VARIABLES, MAX_TIMESTEPS))
# stride = 3
#
# x = Permute((2, 1))(ip)
# x = Conv1D(MAX_NB_VARIABLES // stride, 8, strides=stride, padding='same', activation='relu', use_bias=False,
# kernel_initializer='he_uniform')(x) # (None, variables / stride, timesteps)
# x = Permute((2, 1))(x)
x = Masking()(ip)
x = AttentionLSTM(8)(x)
x = Dropout(0.8)(x)
y = Permute((2, 1))(ip)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
#y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
#y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(NB_CLASS, activation='softmax')(x)
model = Model(ip, out)
model.summary()
# add load model code here to fine-tune
return model
Example 46
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 5 votes |
|
def weather_mve(hidden_nums=100):
input_img = Input(shape=(37,))
hn = Dense(hidden_nums, activation='relu')(input_img)
hn = Dense(hidden_nums, activation='relu')(hn)
out_u = Dense(37, activation='sigmoid', name='ae_part')(hn)
out_sig = Dense(37, activation='linear', name='pred_part')(hn)
out_both = concatenate([out_u, out_sig], axis=1, name = 'concatenate')
#weather_model = Model(input_img, outputs=[out_ae, out_pred])
mve_model = Model(input_img, outputs=[out_both])
mve_model.compile(optimizer='adam', loss=mve_loss, loss_weights=[1.])
return mve_model
Example 47
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 5 votes |
|
def weather_mse():
input_img = Input(shape=(37,))
hn = Dense(100, activation='relu')(input_img)
hn = Dense(100, activation='relu')(hn)
out_pred = Dense(37, activation='sigmoid', name='pred_part')(hn)
weather_model = Model(input_img, outputs=[out_pred])
weather_model.compile(optimizer='adam', loss='mse',loss_weights=[1.])
return weather_model
Example 48
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 5 votes |
|
def weather_fnn(layers, lr,
decay, loss, seq_len,
input_features, output_features):
ori_inputs = Input(shape=(seq_len, input_features), name='input_layer')
#print(seq_len*input_features)
conv_ = Conv1D(11, kernel_size=13, strides=1,
data_format='channels_last',
padding='valid', activation='linear')(ori_inputs)
conv_ = BatchNormalization(name='BN_conv')(conv_)
conv_ = Activation('relu')(conv_)
conv_ = Conv1D(5, kernel_size=7, strides=1,
data_format='channels_last',
padding='valid', activation='linear')(conv_)
conv_ = BatchNormalization(name='BN_conv2')(conv_)
conv_ = Activation('relu')(conv_)
inputs = Reshape((-1,))(conv_)
for i, hidden_nums in enumerate(layers):
if i==0:
hn = Dense(hidden_nums, activation='linear')(inputs)
hn = BatchNormalization(name='BN_{}'.format(i))(hn)
hn = Activation('relu')(hn)
else:
hn = Dense(hidden_nums, activation='linear')(hn)
hn = BatchNormalization(name='BN_{}'.format(i))(hn)
hn = Activation('relu')(hn)
#hn = Dropout(0.1)(hn)
#print(seq_len, output_features)
#print(hn)
outputs = Dense(seq_len*output_features, activation='sigmoid', name='output_layer')(hn) # 37*3
outputs = Reshape((seq_len, output_features))(outputs)
weather_fnn = Model(ori_inputs, outputs=[outputs])
return weather_fnn
Example 49
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 5 votes |
|
def weather_fusion():
input_img = Input(shape=(37,))
hn = Dense(100, activation='relu')(input_img)
hn = Dense(100, activation='relu')(hn)
#out_ae = Dense(37, activation='sigmoid', name='ae_part')(hn)
out_pred = Dense(37, activation='sigmoid', name='pred_part')(hn)
weather_model = Model(input_img, outputs=[out_ae, out_pred])
weather_model.compile(optimizer='adam', loss='mse',loss_weights=[1.5, 1.])
return weather_model
Example 50
| Project: Jetson-RaceCar-AI Author: ardamavi File: get_model.py Apache License 2.0 | 5 votes |
|
def get_model():
img_inputs = Input(shape=(500, 500, 1))
lidar_inputs = Input(shape=(3,))
conv_1 = Conv2D(32, (4,4), strides=(2,2))(img_inputs)
conv_2 = Conv2D(32, (4,4), strides=(2,2))(conv_1)
conv_3 = Conv2D(32, (3,3), strides=(1,1))(conv_2)
act_3 = Activation('relu')(conv_3)
pooling_1 = MaxPooling2D(pool_size=(2, 2), strides=(2, 2))(act_3)
flat_1 = Flatten()(pooling_1)
fc = Dense(32)(flat_1)
lidar_fc = Dense(32)(lidar_inputs)
concatenate_layer = concatenate([fc, lidar_fc])
fc = Dense(10)(concatenate_layer)
fc = Activation('relu')(fc)
fc = Dropout(0.5)(fc)
outputs = Dense(2)(fc)
outputs = Activation('sigmoid')(outputs)
model = Model(inputs=[img_inputs, lidar_inputs], outputs=[outputs])
model.compile(loss='mse', optimizer='adadelta', metrics=['accuracy'])
print(model.summary())
return model
Example 51
| Project: Kaggler Author: jeongyoonlee File: categorical.py MIT License | 5 votes |
|
def _get_model(X, cat_cols, num_cols, n_uniq, n_emb, output_activation):
inputs = []
num_inputs = []
embeddings = []
for i, col in enumerate(cat_cols):
if not n_uniq[i]:
n_uniq[i] = X[col].nunique()
if not n_emb[i]:
n_emb[i] = max(MIN_EMBEDDING, 2 * int(np.log2(n_uniq[i])))
_input = Input(shape=(1,), name=col)
_embed = Embedding(input_dim=n_uniq[i], output_dim=n_emb[i], name=col + EMBEDDING_SUFFIX)(_input)
_embed = Dropout(.2)(_embed)
_embed = Reshape((n_emb[i],))(_embed)
inputs.append(_input)
embeddings.append(_embed)
if num_cols:
num_inputs = Input(shape=(len(num_cols),), name='num_inputs')
merged_input = Concatenate(axis=1)(embeddings + [num_inputs])
inputs = inputs + [num_inputs]
else:
merged_input = Concatenate(axis=1)(embeddings)
x = BatchNormalization()(merged_input)
x = Dense(128, activation='relu')(x)
x = Dropout(.5)(x)
x = BatchNormalization()(x)
x = Dense(64, activation='relu')(x)
x = Dropout(.5)(x)
x = BatchNormalization()(x)
output = Dense(1, activation=output_activation)(x)
model = Model(inputs=inputs, outputs=output)
return model, n_emb, n_uniq
Example 52
| Project: dac Author: KBNLresearch File: models.py GNU General Public License v3.0 | 5 votes |
|
def create_model(self):
'''
Create new keras model.
'''
self.class_weight = {0: 0.25, 1: 0.75}
model = Sequential()
model.add(Dense(self.data.shape[1], input_dim=self.data.shape[1],
activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.5))
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='RMSprop', loss='binary_crossentropy',
metrics=['accuracy'])
return model
Example 53
| Project: keras-utility-layer-collection Author: zimmerrol File: attention.py MIT License | 5 votes |
|
def build(self, input_shape):
self._validate_input_shape(input_shape)
d_k = self._d_k if self._d_k else input_shape[1][-1]
d_model = self._d_model if self._d_model else input_shape[1][-1]
d_v = self._d_v
if type(d_k) == tf.Dimension:
d_k = d_k.value
if type(d_model) == tf.Dimension:
d_model = d_model.value
self._q_layers = []
self._k_layers = []
self._v_layers = []
self._sdp_layer = ScaledDotProductAttention(return_attention=self._return_attention)
for _ in range(self._h):
self._q_layers.append(
TimeDistributed(
Dense(d_k, activation=self._activation, use_bias=False)
)
)
self._k_layers.append(
TimeDistributed(
Dense(d_k, activation=self._activation, use_bias=False)
)
)
self._v_layers.append(
TimeDistributed(
Dense(d_v, activation=self._activation, use_bias=False)
)
)
self._output = TimeDistributed(Dense(d_model))
#if self._return_attention:
# self._output = Concatenate()
Example 54
| Project: wrangle Author: autonomio File: create_synth_model.py MIT License | 5 votes |
|
def _base_for_model(mode, n=50, neurons=50):
from keras.models import Sequential
from keras.layers import Dense
from .create_synth_data import create_synth_data
x, y = create_synth_data(mode, n=n)
model = Sequential()
model.add(Dense(neurons,
input_dim=x.shape[1],
activation='relu'))
return x, y, model
Example 55
| Project: wrangle Author: autonomio File: create_synth_model.py MIT License | 5 votes |
|
def create_synth_multi_class_model(n=50, neurons=50):
from keras.layers import Dense
x, y, model = _base_for_model('multi_class', n=n, neurons=neurons)
model.add(Dense(4))
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy')
model.fit(x, y)
return model
Example 56
| Project: wrangle Author: autonomio File: create_synth_model.py MIT License | 5 votes |
|
def create_synth_regression_model(n=50, neurons=50):
from keras.layers import Dense
x, y, model = _base_for_model('regression', n=n, neurons=neurons)
model.add(Dense(1))
model.compile(optimizer='sgd', loss='mean_absolute_percentage_error')
model.fit(x, y)
return model
Example 57
| Project: wrangle Author: autonomio File: create_synth_model.py MIT License | 5 votes |
|
def create_synth_multi_label_model(n=50, neurons=50):
from keras.layers import Dense
x, y, model = _base_for_model('multi_label', n=n, neurons=neurons)
model.add(Dense(4, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy')
model.fit(x, y)
return model
Example 58
| Project: wrangle Author: autonomio File: create_synth_model.py MIT License | 5 votes |
|
def create_synth_binary_model(n=50, neurons=50):
from keras.layers import Dense
x, y, model = _base_for_model('binary', n=n, neurons=neurons)
model.add(Dense(1, activation='sigmoid'))
model.compile(optimizer='adam', loss='binary_crossentropy')
model.fit(x, y)
return model
Example 59
| Project: phoneticSimilarity Author: ronggong File: models_RNN_regression.py GNU Affero General Public License v3.0 | 5 votes |
|
def embedding_RNN(input_shape):
input = Input(shape=input_shape)
x = Bidirectional(LSTM(units=16, return_sequences=False))(input)
outputs = Dense(1, activation='linear')(x)
model = Model(inputs=input, outputs=outputs)
model.compile(optimizer='adam',
loss='mse',
metrics=['accuracy'])
# model.summary()
return model
Example 60
| Project: phoneticSimilarity Author: ronggong File: models_siamese_tripletloss.py GNU Affero General Public License v3.0 | 5 votes |
|
def embedding_2_lstm_1_dense_base(device, base_input):
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=True))(base_input)
x = Bidirectional(LSTM(units=32, return_sequences=False))(x)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=True))(base_input)
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(x)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x
Example 61
| Project: phoneticSimilarity Author: ronggong File: models_siamese_tripletloss.py GNU Affero General Public License v3.0 | 5 votes |
|
def embedding_1_lstm_1_dense_base(device, base_input):
if device == 'CPU':
x = Bidirectional(LSTM(units=32, return_sequences=False))(base_input)
else:
x = Bidirectional(CuDNNLSTM(units=32, return_sequences=False))(base_input)
x = Dense(units=64, activation='relu')(x)
x = Dropout(rate=0.5)(x)
return x
Example 62
| Project: phoneticSimilarity Author: ronggong File: models_siamese_tripletloss.py GNU Affero General Public License v3.0 | 5 votes |
|
def embedding_base_model(input_shape, output_shape, base_model):
device = device_lib.list_local_devices()[0].device_type
# embedding base model
base_input = Input(batch_shape=input_shape)
x = base_model(device, base_input)
x = Dense(output_shape, activation='linear', name='embedding_layer')(x)
embedding_model = Model(inputs=base_input, outputs=x, name='embedding')
return embedding_model
Example 63
| Project: phoneticSimilarity Author: ronggong File: cal_embeddigns_for_plotting.py GNU Affero General Public License v3.0 | 5 votes |
|
def calculate_overall_quality_score(list_feature_teacher, list_feature_student):
"""
Calculate overall quality similarity
:param list_feature_teacher:
:param list_feature_student:
:return:
"""
path_model = '/home/gong/Documents/pycharmProjects/phoneticSimilarity/models/phone_embedding_classifier'
path_dataset = '/media/gong/ec990efa-9ee0-4693-984b-29372dcea0d1/Data/RongGong/phoneEmbedding'
config = [1, 0]
input_shape = [1, None, 80]
embedding_dim = 32
prefix = '_2_class_teacher_student'
attention_dense_str = "dense_32_"
model_name = config_select(config) + prefix
filename_model = os.path.join(path_model, model_name + '_' + attention_dense_str + str(0) + '.h5')
filename_scaler = os.path.join(path_dataset, 'scaler_phn_embedding_train_teacher_student.pkl')
model = load_model(filepath=filename_model, custom_objects={'Attention': Attention(return_attention=True)})
weights = model.get_weights()
x, input = model_select(config=config, input_shape=input_shape, conv=False, dropout=False)
outputs = Dense(embedding_dim)(x)
model_1_batch = Model(inputs=input, outputs=outputs)
model_1_batch.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model_1_batch.set_weights(weights=weights)
scaler = pickle.load(open(filename_scaler, 'rb'))
list_simi = []
for ii in range(len(list_feature_teacher)):
x_batch_teacher = np.expand_dims(scaler.transform(list_feature_teacher[ii]), axis=0)
x_batch_student = np.expand_dims(scaler.transform(list_feature_student[ii]), axis=0)
embedding_teacher = model_1_batch.predict_on_batch(x_batch_teacher)
embedding_student = model_1_batch.predict_on_batch(x_batch_student)
dist = (2.0 - cosine(embedding_teacher, embedding_student)) / 2.0
list_simi.append(dist)
return list_simi
Example 64
| Project: hepaccelerate Author: hepaccelerate File: train_dnn.py BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def layer(din, n_units, do_dropout=False):
d = Dense(n_units)(din)
d = LeakyReLU(alpha=0.2)(d)
if do_dropout:
d = Dropout(0.2)(d)
return d
Example 65
| Project: ppi_lstm_rnn_keras Author: ylhsieh File: train_keras.py MIT License | 5 votes |
|
def main():
def build_model():
model = Sequential()
model.add(Embedding(len(train_vocab), hidden_size, weights=[embedding_array],\
input_length=max_sequence_length))
model.add(Dropout(dropout_rate))
model.add(Bidirectional(LSTM(rnn_hidden_size)))
model.add(Dropout(dropout_rate))
model.add(Dense(2, activation='softmax'))
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
print(model.summary())
return model
train_vocab = load_vocab_from(opt.data + '.vocab')
embedding_array = load_pretrained_embeddings(train_vocab, pretrained_embeddings_file)
for fold_id in range(10):
tfsession = tf.Session(config=tf.ConfigProto(gpu_options=tf.GPUOptions(per_process_gpu_memory_fraction=0.5)))
K.set_session(tfsession)
train_file = 'corpus/{}_f{}_train.txt'.format(opt.data, fold_id)
test_file = 'corpus/{}_f{}_test.txt'.format(opt.data, fold_id)
log_file = '{}_f{}.log'.format(opt.data, fold_id)
x_train, x_test, y_train, y_test, _ = read_corpus(train_file, test_file, train_vocab)
fscore_cb = FscoreLogCallback(log_file)
model = build_model()
print("Fold {}".format(fold_id))
model.fit(x_train, y_train, epochs=epochs, batch_size=batch_size, \
callbacks=[fscore_cb], verbose=2)
predicted = np.argmax(model.predict(x_test), axis=1)
y_test_to_label = np.argmax(y_test, axis=1)
prec, reca, fscore, sup = precision_recall_fscore_support(y_test_to_label, predicted, average='binary')
print("Final Precision:{:2.2f}% Recall:{:2.2f}% Fscore:{:2.2f}%".format(prec*100, reca*100, fscore*100))
Example 66
| Project: Anamoly-Detection Author: msmsk05 File: auto_encoder.py BSD 2-Clause "Simplified" License | 5 votes |
|
def _build_model(self):
model = Sequential()
# Input layer
model.add(Dense(
self.hidden_neurons_[0], activation=self.hidden_activation,
input_shape=(self.n_features_,),
activity_regularizer=l2(self.l2_regularizer)))
model.add(Dropout(self.dropout_rate))
# Additional layers
for i, hidden_neurons in enumerate(self.hidden_neurons_, 1):
model.add(Dense(
hidden_neurons,
activation=self.hidden_activation,
activity_regularizer=l2(self.l2_regularizer)))
model.add(Dropout(self.dropout_rate))
# Output layers
model.add(Dense(self.n_features_, activation=self.output_activation,
activity_regularizer=l2(self.l2_regularizer)))
# Compile model
model.compile(loss=self.loss, optimizer=self.optimizer)
print(model.summary())
return model
# noinspection PyUnresolvedReferences
Example 67
| Project: Anamoly-Detection Author: msmsk05 File: gaal_base.py BSD 2-Clause "Simplified" License | 5 votes |
|
def create_discriminator(latent_size, data_size): # pragma: no cover
"""Create the discriminator of the GAN for a given latent size.
Parameters
----------
latent_size : int
The size of the latent space of the generator.
data_size : int
Size of the input data.
Returns
-------
D : Keras model() object
Returns a model() object.
"""
dis = Sequential()
dis.add(Dense(int(math.ceil(math.sqrt(data_size))),
input_dim=latent_size, activation='relu',
kernel_initializer=keras.initializers.VarianceScaling(
scale=1.0, mode='fan_in', distribution='normal',
seed=None)))
dis.add(Dense(1, activation='sigmoid',
kernel_initializer=keras.initializers.VarianceScaling(
scale=1.0, mode='fan_in', distribution='normal',
seed=None)))
data = Input(shape=(latent_size,))
fake = dis(data)
return Model(data, fake)
Example 68
| Project: MODS_ConvNet Author: santiagolopezg File: little_foo3.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(32, 8, 8,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 6, 6,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 4, 4,init=weight_init, name='conv1_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 2, 2,init=weight_init, name='conv1_4'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in 208, out 104
model.add(Dropout(dropout))
model.add(Convolution2D(64, 8, 8,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 6, 6,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 4, 4,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 2, 2,init=weight_init, name='conv2_4'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in is 88, out is 44
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(220, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 69
| Project: MODS_ConvNet Author: santiagolopezg File: foo_three.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(32, 3, 3,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(512, 3,3,init=weight_init, border_mode='same', name='conv4_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(512, 3,3,init=weight_init, border_mode='same', name='conv4_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(120, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 70
| Project: MODS_ConvNet Author: santiagolopezg File: little_foo.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(32, 5, 5,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv1_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in 116, out 58
model.add(Dropout(dropout))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in is 52, out is 26
model.add(Dropout(dropout))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in is 20, out is 10
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(10, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 71
| Project: MODS_ConvNet Author: santiagolopezg File: foo_two.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(16, 3, 3,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(16, 3, 3,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv3_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv3_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(128, 3,3,init=weight_init, border_mode='same', name='conv4_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(128, 3,3,init=weight_init, border_mode='same', name='conv4_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(120, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 72
| Project: MODS_ConvNet Author: santiagolopezg File: foo_three.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(32, 3, 3,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(128, 3, 3,init=weight_init, name='conv3_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Convolution2D(512, 3,3,init=weight_init, border_mode='same', name='conv4_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(512, 3,3,init=weight_init, border_mode='same', name='conv4_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(120, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 73
| Project: MODS_ConvNet Author: santiagolopezg File: little_foo2.py MIT License | 4 votes |
|
def foo():
# Determine proper input shape
if keras.__version__ > '1.0.3':
K.set_image_dim_ordering('th')
input_shape = (1, 224, 224)
#img_input = Input(shape=input_shape)
model = Sequential()
model.add(Convolution2D(32, 7, 7,
input_shape=input_shape,init=weight_init, name='conv1_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 5, 5,init=weight_init, name='conv1_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(32, 3, 3,init=weight_init, name='conv1_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in 212, out 106
model.add(Dropout(dropout))
model.add(Convolution2D(64, 7, 7,init=weight_init, name='conv2_1'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 5, 5,init=weight_init, name='conv2_2'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(Convolution2D(64, 3, 3,init=weight_init, name='conv2_3'))
model.add(BatchNormalization())
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2))) # in is 94, out is 47
model.add(Dropout(dropout))
model.add(Flatten())
model.add(Dense(220, init=weight_init))
model.add(Activation('relu'))
model.add(Dropout(dropout))
model.add(Dense(2))
model.add(Activation('sigmoid'))
return model
Example 74
| Project: Scene-Understanding Author: foamliu File: vgg16.py MIT License | 4 votes |
|
def vgg16_model(img_rows, img_cols, channel=3):
model = Sequential()
# Encoder
model.add(ZeroPadding2D((1, 1), input_shape=(img_rows, img_cols, channel), name='input'))
model.add(Conv2D(64, (3, 3), activation='relu', name='conv1_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(64, (3, 3), activation='relu', name='conv1_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(128, (3, 3), activation='relu', name='conv2_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(128, (3, 3), activation='relu', name='conv2_2'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(256, (3, 3), activation='relu', name='conv3_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(256, (3, 3), activation='relu', name='conv3_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(256, (3, 3), activation='relu', name='conv3_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv4_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv4_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv4_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv5_1'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv5_2'))
model.add(ZeroPadding2D((1, 1)))
model.add(Conv2D(512, (3, 3), activation='relu', name='conv5_3'))
model.add(MaxPooling2D((2, 2), strides=(2, 2)))
# Add Fully Connected Layer
model.add(Flatten(name='flatten'))
model.add(Dense(4096, activation='relu', name='dense1'))
model.add(Dropout(0.5))
model.add(Dense(4096, activation='relu', name='dense2'))
model.add(Dropout(0.5))
model.add(Dense(1000, activation='softmax', name='softmax'))
# Loads ImageNet pre-trained data
weights_path = 'models/vgg16_weights_tf_dim_ordering_tf_kernels.h5'
model.load_weights(weights_path)
return model
Example 75
| Project: smach_based_introspection_framework Author: birlrobotics File: anomaly_model_generation.py BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def generate_model():
ip = Input(shape=(MAX_NB_VARIABLES, MAX_TIMESTEPS))
x = Masking()(ip)
x = LSTM(8)(x)
x = Dropout(0.8)(x)
y = Permute((2, 1))(ip)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(NB_CLASS, activation='softmax')(x)
model = Model(ip, out)
model.summary()
# add load model code here to fine-tune
return model
Example 76
| Project: smach_based_introspection_framework Author: birlrobotics File: anomaly_model_generation.py BSD 3-Clause "New" or "Revised" License | 4 votes |
|
def generate_model_2():
ip = Input(shape=(MAX_NB_VARIABLES, MAX_TIMESTEPS))
# stride = 10
# x = Permute((2, 1))(ip)
# x = Conv1D(MAX_NB_VARIABLES // stride, 8, strides=stride, padding='same', activation='relu', use_bias=False,
# kernel_initializer='he_uniform')(x) # (None, variables / stride, timesteps)
# x = Permute((2, 1))(x)
#ip1 = K.reshape(ip,shape=(MAX_TIMESTEPS,MAX_NB_VARIABLES))
#x = Permute((2, 1))(ip)
x = Masking()(ip)
x = AttentionLSTM(8)(x)
x = Dropout(0.8)(x)
y = Permute((2, 1))(ip)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(NB_CLASS, activation='softmax')(x)
model = Model(ip, out)
model.summary()
# add load model code here to fine-tune
return model
Example 77
| Project: Deep_Learning_Weather_Forecasting Author: BruceBinBoxing File: weather_model.py Apache License 2.0 | 4 votes |
|
def RNN_builder(num_output_features, num_decoder_features,
target_sequence_length,
num_steps_to_predict, regulariser,
lr, decay, loss, layers):
optimiser = keras.optimizers.Adam(lr=lr, decay=decay)
# Define a decoder sequence.
decoder_inputs = keras.layers.Input(shape=(37, num_decoder_features), name='decoder_inputs')
decoder_cells = []
for hidden_neurons in layers:
print(hidden_neurons)
decoder_cells.append(keras.layers.GRUCell(hidden_neurons,
kernel_regularizer = regulariser,
recurrent_regularizer = regulariser,
bias_regularizer = regulariser))
print(decoder_cells)
decoder = keras.layers.RNN(decoder_cells, return_sequences=True, return_state=True)
# Set the initial state of the decoder to be the ouput state of the encoder.
decoder_outputs_and_states = decoder(decoder_inputs, initial_state=None)
# Only select the output of the decoder (not the states)
decoder_outputs = decoder_outputs_and_states[0]
# Apply a dense layer with linear activation to set output to correct dimension
# and scale (tanh is default activation for GRU in Keras, our output sine function can be larger then 1)
#decoder_dense1 = keras.layers.Dense(units=64,
# activation='tanh',
# kernel_regularizer = regulariser,
# bias_regularizer = regulariser, name='dense_tanh')
output_dense = keras.layers.Dense(num_output_features,
activation='sigmoid',
kernel_regularizer = regulariser,
bias_regularizer = regulariser, name='output_sig')
#densen1=decoder_dense1(decoder_outputs)
decoder_outputs = output_dense(decoder_outputs)
# Create a model using the functional API provided by Keras.
rnn_model = keras.models.Model(inputs=[decoder_inputs], outputs=decoder_outputs)
return rnn_model
Example 78
| Project: dac Author: KBNLresearch File: models.py GNU General Public License v3.0 | 4 votes |
|
def create_model(self):
'''
Create new keras model.
'''
self.class_weight = {0: 0.25, 1: 0.75}
# Entity branch
entity_inputs = Input(shape=(self.data[0].shape[1],))
entity_x = Dense(self.data[0].shape[1], activation='relu',
kernel_constraint=maxnorm(3))(entity_inputs)
entity_x = Dropout(0.25)(entity_x)
# entity_x = Dense(50, activation='relu',
# self.kernel_constraint=maxnorm(3))(entity_x)
# entity_x = Dropout(0.25)(entity_x)
# Candidate branch
candidate_inputs = Input(shape=(self.data[1].shape[1],))
candidate_x = Dense(self.data[1].shape[1], activation='relu',
kernel_constraint=maxnorm(3))(candidate_inputs)
candidate_x = Dropout(0.25)(candidate_x)
# candidate_x = Dense(50, activation='relu',
# kernel_constraint=maxnorm(3))(candidate_x)
# candidate_x = Dropout(0.25)(candidate_x)
# Cosine proximity
# cos_x = dot([entity_x, candidate_x], axes=1, normalize=False)
# cos_x = concatenate([entity_x, candidate_x])
# cos_output = Dense(1, activation='sigmoid')(cos_x)
# Match branch
match_inputs = Input(shape=(self.data[2].shape[1],))
match_x = Dense(self.data[1].shape[1], activation='relu',
kernel_constraint=maxnorm(3))(match_inputs)
match_x = Dropout(0.25)(match_x)
# Merge
x = concatenate([entity_x, candidate_x, match_x])
x = Dense(32, activation='relu', kernel_constraint=maxnorm(3))(x)
x = Dropout(0.25)(x)
x = Dense(16, activation='relu', kernel_constraint=maxnorm(3))(x)
x = Dropout(0.25)(x)
x = Dense(8, activation='relu', kernel_constraint=maxnorm(3))(x)
x = Dropout(0.25)(x)
predictions = Dense(1, activation='sigmoid')(x)
model = Model(inputs=[entity_inputs, candidate_inputs, match_inputs],
outputs=predictions)
model.compile(optimizer='RMSprop', loss='binary_crossentropy',
metrics=['accuracy'])
return model
Example 79
| Project: phoneticSimilarity Author: ronggong File: models.py GNU Affero General Public License v3.0 | 4 votes |
|
def jan_original(filter_density, dropout, input_shape, batchNorm=False, dense_activation='relu', channel=1):
if channel == 1:
reshape_dim = (1, input_shape[0], input_shape[1])
channel_order = 'channels_first'
else:
reshape_dim = input_shape
channel_order = 'channels_last'
model_1 = Sequential()
if batchNorm:
model_1.add(BatchNormalization(axis=1, input_shape=reshape_dim))
model_1.add(Conv2D(int(10 * filter_density), (3, 7), padding="valid",
input_shape=reshape_dim,
data_format=channel_order, activation='relu'))
model_1.add(MaxPooling2D(pool_size=(3, 1), padding='valid', data_format=channel_order))
model_1.add(Conv2D(int(20 * filter_density), (3, 3), padding="valid",
data_format=channel_order, activation='relu'))
model_1.add(MaxPooling2D(pool_size=(3, 1), padding='valid', data_format=channel_order))
if dropout:
model_1.add(Dropout(dropout)) # test Schluter dataset, comment in jingju dataset
model_1.add(Flatten())
model_1.add(Dense(units=256, activation=dense_activation))
# model_1.add(ELU())
if dropout:
model_1.add(Dropout(dropout))
model_1.add(Dense(1, activation='sigmoid'))
# model_1.add(Activation("softmax"))
# optimizer = SGD(lr=0.05, momentum=0.45, decay=0.0, nesterov=False)
optimizer = Adam()
model_1.compile(loss='binary_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
print(model_1.summary())
return model_1
Example 80
| Project: phoneticSimilarity Author: ronggong File: cal_embeddigns_for_plotting.py GNU Affero General Public License v3.0 | 4 votes |
|
def calculate_pronunciation_score(list_feature_teacher, list_feature_student):
"""
Calculate pronunciation similarity
:param list_feature_teacher:
:param list_feature_student:
:return:
"""
path_model = '/home/gong/Documents/pycharmProjects/phoneticSimilarity/models/phone_embedding_classifier'
path_dataset = '/media/gong/ec990efa-9ee0-4693-984b-29372dcea0d1/Data/RongGong/phoneEmbedding'
conv = True
dropout = True
config = [2, 0]
input_shape = [1, None, 80]
embedding_dim = 27
prefix = '_27_class'
attention_dense_str = 'attention_conv_dropout_'
model_name = config_select(config)
filename_model = os.path.join(path_model, model_name + prefix + '_' + attention_dense_str + str(0) + '.h5')
filename_scaler = os.path.join(path_dataset, 'scaler_phn_embedding_train_teacher_student.pkl')
# loading models
model = load_model(filepath=filename_model, custom_objects={'Attention': Attention(return_attention=True)})
weights = model.get_weights()
x, input, _ = model_select_attention(config=config, input_shape=input_shape, conv=conv, dropout=dropout)
outputs = Dense(embedding_dim, activation='softmax')(x)
model_1_batch = Model(inputs=input, outputs=outputs)
model_1_batch.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model_1_batch.set_weights(weights=weights)
scaler = pickle.load(open(filename_scaler, 'rb'))
# calculate the similarity
list_simi = []
for ii in range(len(list_feature_teacher)):
x_batch_teacher = np.expand_dims(scaler.transform(list_feature_teacher[ii]), axis=0)
x_batch_student = np.expand_dims(scaler.transform(list_feature_student[ii]), axis=0)
embedding_teacher = model_1_batch.predict_on_batch(x_batch_teacher)
embedding_student = model_1_batch.predict_on_batch(x_batch_student)
dist = (2.0 - cosine(embedding_teacher, embedding_student)) / 2.0
list_simi.append(dist)
return list_simi
