def test_construct_nn():
nn = NeuralNetwork(2)
nn.add_layer(Dense(40))
nn.add_layer(Activation('relu'))
nn.add_layer(Dense(2))
nn.add_layer(Activation('softmax'))
assert len(nn.layers) == 4
assert not hasattr(nn, 'train_fn')
nn.compile(categorical_crossentropy, argmax)
assert hasattr(nn, 'train_fn')
num_hidden_nodes = 784
num_training_iterations = 1000
# Get the cifar10 dataset
print("Getting data...")
(X_train, y_train), (X_test, y_test) = data.get_mnist()
# Compile network
print("Compiling model...", end='')
nn = NeuralNetwork(X_train.shape[1])
for x in range(num_layers):
nn.add_layer(Dense(num_hidden_nodes))
get_layer_for_setting(nn, setting)
nn.add_layer(Dense(10))
nn.add_layer(Activation('softmax'))
nn.compile(loss_fn='categorical_crossentropy', init_fn='lecun', pred_fn='argmax',
learning_rate=learning_rate, use_normal=True)
print('finished!')
ap_loss = []
for i in range(1, num_training_iterations+1):
start = time()
nn.train(X_train, y_train)
time_elapsed = time() - start
s = "{},{},{}".format(i, nn.get_accuracy(X_train, y_train), time_elapsed)
print(s)
f.write(s+'\n')
#ap_loss.append()
#print(ap_loss[-1])
# Plotting
#import matplotlib.pyplot as plt
1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])
y = data.one_hot_encode(y)
ap_losses = []
relu_losses = []
for x in range(trials):
nn = NeuralNetwork(4)
for x in range(num_layers):
nn.add_layer(Dense(num_hidden_nodes))
nn.add_layer(ActivationPool(act_fns))
nn.add_layer(Dense(3))
nn.add_layer(Activation('softmax'))
nn.compile(loss_fn='categorical_crossentropy', pred_fn='argmax', learning_rate=learning_rate)
ap_losses.append(nn.get_loss(X, y))
for x in range(trials):
nn = NeuralNetwork(4)
for x in range(num_layers):
nn.add_layer(Dense(num_hidden_nodes))
nn.add_layer(Activation('relu'))
nn.add_layer(Dense(3))
nn.add_layer(Activation('softmax'))
nn.compile(loss_fn='categorical_crossentropy', pred_fn='argmax', learning_rate=learning_rate)
relu_losses.append(nn.get_loss(X, y))
print(describe(ap_losses))
print(describe(relu_losses))