def __init__(self, dict_size: int, embedding_size: int, hidden_units: int):
self.layers = [layer.Embedding(dict_size, embedding_size, 'l0-Embedding'),
layer.Recursive(embedding_size, hidden_units, 'l1-R'),
layer.Tanh(hidden_units, 'l2-Tanh'),
layer.Linear(hidden_units, dict_size, 'l3-L'),
layer.Softmax(dict_size, 'l4-Softmax')]
self.h: list = None
return
def __init__(self, dict_size: int, embedding_size: int, hidden_units: int):
self.layers = [layer.Embedding(dict_size, embedding_size, 'l0'),
layer.Linear(embedding_size, hidden_units, 'l1-0'),
layer.Linear(embedding_size, hidden_units, 'l1-1'),
layer.Linear(embedding_size, hidden_units, 'l1-2'),
layer.Linear(hidden_units, dict_size, 'l2'),
layer.Softmax(dict_size, 'l3')]
self.h: list = None
return
def __init__(self, dict_size: int, embedding_size: int, hidden_units: int):
self.layers = [layer.Embedding(dict_size, embedding_size, 'l0'), # layer 0
layer.Linear(embedding_size, hidden_units, 'l1-0'), # layer 1
layer.Linear(embedding_size, hidden_units, 'l1-1'), # layer 2
layer.Linear(embedding_size, hidden_units, 'l1-2'), # layer 3
layer.Tanh(hidden_units, 'l2'), # layer 4
layer.Linear(hidden_units, dict_size, 'l3'), # layer 5
layer.Softmax(dict_size, 'l4')] # layer 6
self.h: list = None
return
print('Settings 3')
train_settings = TrainSettings(learning_rate=0.005,
batch_size=16,
momentum=0.0,
plot_callback=cb.plot_callback,
loss_callback=cb.loss_callback,
filename='script-1-1-3',
epoch=200,
prefix='e16')
layers = [
layer.Linear(784, 100),
#layer.BN(100, 100),
layer.Sigmoid(100),
layer.Linear(100, 10),
layer.Softmax(10)
]
mynn = network.MLP(layers)
utf.cross_train(mynn, data_store_train, data_store_valid, train_settings)
print('Settings 4')
train_settings = TrainSettings(learning_rate=0.01,
batch_size=16,
momentum=0.0,
plot_callback=cb.plot_callback,
loss_callback=cb.loss_callback,
filename='script-1-1-4',
epoch=300,
prefix='e16')
import os
# format of data
# disitstrain.txt contains 3000 lines, each line 785 numbers, comma delimited
full_path = os.path.realpath(__file__)
path, filename = os.path.split(full_path)
data_filepath = '../data'
data_train_filename = 'digitstrain.txt'
data_valid_filename = 'digitsvalid.txt'
data_test_filename = 'digitstest.txt'
data_train_filepath = os.path.join(path, data_filepath, data_train_filename)
data_valid_filepath = os.path.join(path, data_filepath, data_valid_filename)
data_test_filepath = os.path.join(path, data_filepath, data_test_filename)
print('start initializing...')
network.init_nn(random_seed=1099)
x_train, y_train = load_data.load_from_path(data_train_filepath)
x_valid, y_valid = load_data.load_from_path(data_valid_filepath)
layers = [
layer.Linear(784, 100),
layer.Tanh(100, 100),
layer.Linear(100, 100),
layer.Softmax(10, 10)
]
myNN = NN(layers, learning_rate=0.1, regularizer=0.0001, momentum=0.9)
myNN.train(x_train, y_train, x_valid, y_valid, epoch=300, batch_size=32)