def training_data(tmpdir_factory):
import h5py
from keras.layers import Dense
from keras.models import Sequential
from keras.optimizers import SGD
from keras.initializers import glorot_normal, normal
from deepreplay.datasets.parabola import load_data
from deepreplay.callbacks import ReplayData
filename = str(tmpdir_factory.mktemp('data').join('training.h5'))
X, y = load_data(xlim=(-1, 1), n_points=1000, shuffle=True, seed=13)
sgd = SGD(lr=0.05)
glorot_initializer = glorot_normal(seed=42)
normal_initializer = normal(seed=42)
replaydata = ReplayData(X,
y,
filename=filename,
group_name='part1_activation_functions')
np.random.seed(13)
model = Sequential()
model.add(
Dense(input_dim=2,
units=2,
kernel_initializer=glorot_initializer,
activation='sigmoid',
name='hidden'))
model.add(
Dense(units=1,
kernel_initializer=normal_initializer,
activation='sigmoid',
name='output'))
model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['acc'])
model.fit(X, y, epochs=20, batch_size=16, callbacks=[replaydata])
training_data = h5py.File(filename, 'r')
return training_data['part1_activation_functions']
def training_data(tmpdir_factory):
import h5py
from keras.layers import Dense
from keras.models import Sequential
from keras.optimizers import SGD
from keras.initializers import glorot_normal, normal
from deepreplay.datasets.parabola import load_data
from deepreplay.callbacks import ReplayData
filename = str(tmpdir_factory.mktemp('data').join('training.h5'))
X, y = load_data(xlim=(-1, 1), n_points=1000, shuffle=True, seed=13)
sgd = SGD(lr=0.05)
glorot_initializer = glorot_normal(seed=42)
normal_initializer = normal(seed=42)
replaydata = ReplayData(X, y, filename=filename, group_name='part1_activation_functions')
model = Sequential()
model.add(Dense(input_dim=2,
units=2,
kernel_initializer=glorot_initializer,
activation='sigmoid',
name='hidden'))
model.add(Dense(units=1,
kernel_initializer=normal_initializer,
activation='sigmoid',
name='output'))
model.compile(loss='binary_crossentropy',
optimizer=sgd,
metrics=['acc'])
model.fit(X, y, epochs=20, batch_size=16, callbacks=[replaydata])
training_data = h5py.File(filename, 'r')
return training_data['part1_activation_functions']
from deepreplay.callbacks import ReplayData
from deepreplay.datasets.parabola import load_data
X, y = load_data()
replaydata = ReplayData(X,
y,
filename='hyperparams_in_action.h5',
group_name='part1')
from keras.models import Sequential
from keras.layers import Dense
from keras.optimizers import SGD
from keras.initializers import glorot_normal, normal
model = Sequential()
model.add(
Dense(input_dim=2,
units=2,
activation='sigmoid',
kernel_initializer=glorot_normal(seed=42),
name='hidden'))
model.add(
Dense(units=1,
activation='sigmoid',
kernel_initializer=normal(seed=42),
name='output'))
model.compile(loss='binary_crossentropy',
optimizer=SGD(lr=0.05),
metrics=['acc'])
from keras.layers import Dense, Activation, BatchNormalization
from keras.models import Sequential
from keras.optimizers import SGD
from keras.initializers import glorot_normal, normal
from deepreplay.datasets.parabola import load_data
from deepreplay.callbacks import ReplayData
X, y = load_data()
sgd = SGD(lr=0.05)
def basic_model(activation, initializers):
model = Sequential()
model.add(Dense(units=2,
input_dim=2,
kernel_initializer=initializers[0],
activation=activation,
name='hidden'))
model.add(Dense(units=1,
kernel_initializer=initializers[1],
activation='sigmoid',
name='output'))
return model
def bn_model(activation, initializers):
model = Sequential()
model.add(Dense(units=2,
input_dim=2,
kernel_initializer=initializers[0],
name='hidden_linear'))