def test_single_initializer(initializer):
model = NeuralNetwork(
optimizer=AdamOptimizer(
learning_rate=default_parameters['learning_rate']),
loss=CrossEntropy(),
layers=[
Flatten(),
Dense(layer_size=50,
activation_func=ReLu(),
weight_initializer=initializer),
Dense(layer_size=10,
activation_func=Softmax(),
weight_initializer=initializer)
],
callbacks=[
LoggerCallback(),
PlotCallback(f'./lab_3/initializers/{initializer.get_name()}')
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
def test_single_cost_and_last_layer(cost_func, last_layer):
model = NeuralNetwork(
optimizer=StaticGradientDescent(default_parameters['learning_rate']),
loss=cost_func,
layers=[
Dense(layer_size=50,
activation_func=ReLu(),
weight_initializer=XavierInitializer()),
Dense(layer_size=10,
activation_func=last_layer,
weight_initializer=XavierInitializer())
],
callbacks=[
LoggerCallback(),
PlotCallback(
f'./lab_3/cost/func={cost_func.get_name()}&last_layer={last_layer.get_name()}'
)
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
def test_single_initializer_with_convo(initializer):
model = NeuralNetwork(
optimizer=AdamOptimizer(
learning_rate=default_parameters['learning_rate'] * 10),
loss=CrossEntropy(),
layers=[
Convolution2D(num_of_filters=8,
kernel=(3, 3),
activation_func=ReLu()),
MaxPooling2D(pool_size=(2, 2), stride=(2, 2)),
Flatten(),
Dense(layer_size=50,
activation_func=ReLu(),
weight_initializer=initializer),
Dense(layer_size=10,
activation_func=Softmax(),
weight_initializer=initializer)
],
callbacks=[
LoggerCallback(),
PlotCallback(f'./lab_3/initializers/{initializer.get_name()}')
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
def test_single_activation_function(activation):
model = NeuralNetwork(
optimizer=StaticGradientDescent(
learning_rate=default_parameters['learning_rate']),
loss=CrossEntropy(),
layers=[
Dense(layer_size=50,
activation_func=activation,
weight_initializer=XavierInitializer()),
Dense(layer_size=10,
activation_func=Softmax(),
weight_initializer=XavierInitializer())
],
callbacks=[
LoggerCallback(),
PlotCallback(f'./results/activations/{activation.get_name()}')
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
def test_single_layer(layer_config):
model = NeuralNetwork(
optimizer=StaticGradientDescent(
learning_rate=default_parameters['learning_rate']),
loss=CrossEntropy(),
layers=layer_config['layers'],
callbacks=[
LoggerCallback(),
PlotCallback(f"./results/layers/{layer_config['name']}")
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
def test_signle_convo_network(test):
model = NeuralNetwork(
optimizer=AdamOptimizer(
learning_rate=default_parameters['learning_rate']),
loss=CrossEntropy(),
layers=test['layers'],
callbacks=[
LoggerCallback(),
PlotCallback(f"./lab_4_fixed/{test['test_name']}")
])
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=default_parameters['epochs'],
batch_size=default_parameters['batch_size'])
model.test(X_test, y_test)
from models.model import NeuralNetwork
from optimizers.gradient_descent_static import StaticGradientDescent
from preprocessing.data_loader import get_data
model = NeuralNetwork(optimizer=StaticGradientDescent(learning_rate=0.01),
loss=MeanSquaredError(),
layers=[
Dense(layer_size=50,
activation_func=ReLu(),
weight_initializer=XavierInitializer()),
Dense(layer_size=10,
activation_func=Softmax(),
weight_initializer=XavierInitializer())
],
callbacks=[
SaveBestCallback('./results/01_10_2019_13:00',
'best_model.pkl'),
LoggerCallback(),
PlotCallback('./results/batch_size/', 'test.pkl')
])
(X_train, y_train), (X_val, y_val), (X_test, y_test) = get_data()
model.fit(x_train=X_train,
y_train=y_train,
x_val=X_val,
y_val=y_val,
epochs=10,
batch_size=32)
model.test(X_test, y_test)