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_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 make_cnn(input_dim, num_of_classes):
conv1 = Convolution(input_dim=input_dim,
pad=2,
stride=2,
num_filters=10,
filter_size=3,
seed=1)
relu1 = Relu()
maxpool1 = Maxpool(input_dim=conv1.output_dim, filter_size=2, stride=1)
flatten = Flatten(seed=1)
dense1 = Dense(input_dim=np.prod(maxpool1.output_dim),
output_dim=num_of_classes,
seed=1)
layers = [conv1, relu1, maxpool1, flatten, dense1]
return layers
(X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes) = load_dataset()
X_train = X_train_orig/255.
X_test = X_test_orig/255.
Y_train = convert_to_one_hot(Y_train_orig, 6).T
Y_test = convert_to_one_hot(Y_test_orig, 6).T
print ("number of training examples = " + str(X_train.shape[0]))
print ("number of test examples = " + str(X_test.shape[0]))
layers = [
Conv((5, 5, 3, 8), strides=1,pad=2, activation=relu, filter_init=lambda shp: np.random.normal(size=shp) * 1.0 / (5*5*3)),
MaxPool(f=8, strides=8, channels = 8),
Conv((3, 3, 8, 16), strides=1,pad=1, activation=relu, filter_init=lambda shp: np.random.normal(size=shp) * 1.0 / (3*3*8)),
MaxPool(f=4, strides=4, channels = 16),
Flatten((2, 2, 16)),
FullyConnected((2*2*16, 20), activation=sigmoid, weight_init=lambda shp: np.random.normal(size=shp) * np.sqrt(1.0 / (2*2*16 + 20))),
FullyConnected((20, 6), activation=linear, weight_init=lambda shp: np.random.normal(size=shp) * np.sqrt(1.0 / ( 20+ 6)))
]
minibatch_size = 20
lr = 0.009
k = 2000
net = Network(layers, lr=lr, loss=cross_entropy)
num_epochs = 10
costs = []
m = X_train.shape[0]
for epoch in range(num_epochs):
import numpy as np
np.random.seed(0)
if __name__ == '__main__':
train_data, train_labels = get_data(num_samples=50000)
test_data, test_labels = get_data(num_samples=10000, dataset="testing")
train_data = train_data / 255
test_data = test_data / 255
print("Train data shape: {}, {}".format(train_data.shape, train_labels.shape))
print("Test data shape: {}, {}".format(test_data.shape, test_labels.shape))
model = Model(
Convolution(filters=5, padding='same'),
Elu(),
Pooling(mode='max', kernel_shape=(2, 2), stride=2),
Flatten(),
FullyConnected(units=10),
Softmax(),
name='cnn5'
)
model.set_loss(CategoricalCrossEntropy)
model.train(train_data, train_labels.T, epochs=2) # set load_and_continue to True if you want to start from already trained weights
# model.load_weights() # uncomment if loading previously trained weights and comment above line to skip training and only load trained weights.
print('Testing accuracy = {}'.format(model.evaluate(test_data, test_labels)))