#activation_functions.PReLU(learning_methods.Momentum(.01,.7),20),
#activation_functions.PReLU(learning_methods.Momentum(.01,.7),30)
network_activations = [activation_functions.Tanh(), \
activation_functions.Softmax()]
def reduceL(t):
for index, v in enumerate(t):
x, y = v
t[index] = x, np.argmax(y)
return t
eta = 3
lmbda = 0
epochs = 64
mini_batch = 10
net=fcnetwork.FCNetwork(network_topology, \
network_activations, \
cost_functions.CrossEntropy(),\
None, \
[bn.BNLayer(learning_methods.Momentum(.01,.7),.06,(30,mini_batch))]\
)
train, valid, test = mnist_loader.load_data_wrapper()
train_list = list(train)
#reg.L2Reg(lbmda,len(train_list))
net.learn(train_list,epochs,mini_batch, \
learning_methods.Momentum(eta,.7,reg.L2Reg(lmbda,len(train_list))), \
test_data=[reduceL(train_list[:10000]),list(test),list(valid)])
import functions as f import activation as act import cost_functions as cost from data_prep import DataPrep from NeuralNetwork import NeuralNetwork # set the parameters n = 100 n_epochs = 300 n_batches = 100 neurons = [50, 50] n_outputs = 10 hidden_act = act.Sigmoid() output_act = act.Softmax() cost_func = cost.CrossEntropy() no_hidden = False seed = 2034 # download MNIST dataset digits = datasets.load_digits() # define input data and labels dataset = digits.images labels = digits.target.reshape(-1, 1) # flatten the image N = len(dataset) dataset = dataset.reshape(N, -1) # Transform labels to onehot vectors and split in train and test