Code: Alles auswählen
import pickle
import numpy as np
class FeedForwardNetwork(object):
def __init__(self, input_dim, hidden_dim, output_dim):
#
# TODO Are those arrays really neccessary or better replaced
# by `None`‽
#
self.input_layer = np.array([])
self.hidden_layer = np.array([])
self.output_layer = np.array([])
self.weights_input_hidden = (
(2 * np.random.random((input_dim, hidden_dim)) - 1) / 1000
)
self.weights_hidden_output = (
(2* np.random.random((hidden_dim, output_dim)) - 1) / 1000
)
#
# TODO Are those arrays really neccessary or better replaced
# by `None`‽
#
self.validation_data = np.array([])
self.validation_data_solution = np.array([])
def set_training_data(self, training_data_input, training_data_target):
"""Splits the data up into training and validation data with a
ratio of 0.75/0.25 and sets the data for training.
"""
if len(training_data_input) != len(training_data_target):
raise ValueError(
'Number of training examples and'
' training targets does not match!'
)
len_training_data = int(len(training_data_input) / 100 * 75)
self.input_layer = training_data_input[:len_training_data]
self.output_layer = training_data_target[:len_training_data]
self.validation_data = np.array(
[training_data_input[len_training_data:]]
)
self.validation_data_solution = np.array(
[training_data_target[len_training_data:]]
)
def save(self, filename):
"""Saves the weights into a pickle file."""
with open(filename, 'wb') as network_file:
pickle.dump(self.weights_input_hidden, network_file)
pickle.dump(self.weights_hidden_output, network_file)
def load(self, filename):
"""Loads network weights from a pickle file."""
with open(filename, 'rb') as network_file:
weights_input_hidden = pickle.load(network_file)
weights_hidden_output = pickle.load(network_file)
if (
len(weights_input_hidden) != len(self.weights_input_hidden)
or len(weights_hidden_output) != len(self.weights_hidden_output)
):
raise ValueError(
'File contains weights that does not'
' match the current networks size!'
)
self.weights_input_hidden = weights_input_hidden
self.weights_hidden_output = weights_hidden_output
def measure_error(self, input_data, output_data):
return 0.5 * np.sum((output_data - self.activate(input_data))**2)
def forward_propagate(self, input_data):
"""Proceeds the input data from input neurons up to output
neurons and returns the output layer.
"""
self.hidden_layer = np.tanh(
np.dot(input_data, self.weights_input_hidden)
)
return np.tanh(np.dot(self.hidden_layer, self.weights_hidden_output))
#: Sends the given input through the net and returns the net's
#: prediction.
activate = forward_propagate
def back_propagate(self, input_data, output_data, eta):
"""Calculates the difference between target output and output
and adjusts the weights to fit the target output better.
The parameter eta is the learning rate.
"""
sample_count = len(input_data)
output_layer = self.forward_propagate(input_data)
output_layer_error = output_data - output_layer
output_layer_delta = output_layer_error * (1 - np.tanh(output_layer)**2)
#
# How much did each hidden neuron contribute to the output
# error? Multiplys delta term with weights.
#
hidden_layer_error = output_layer_delta.dot(
self.weights_hidden_output.T
)
# If the prediction is good, the second term will be small and
# the change will be small.
#
# Ex: target: 1 -> Slope will be 1 so the second term will be big.
#
hidden_layer_delta = (
hidden_layer_error * (1 - np.tanh(self.hidden_layer)**2)
)
# Both lines return a matrix. A row stands for all weights
# connected to one neuron.
#
# E.g. [1, 2, 3] -> Weights to Neuron A
# [4, 5, 6] -> Weights to Neuron B
#
hidden_weights_change = (
self.input_layer.T.dot(hidden_layer_delta) / sample_count
)
output_weights_change = (
self.hidden_layer.T.dot(output_layer_delta) / sample_count
)
self.weights_hidden_output += (
(output_weights_change * eta) / sample_count
)
self.weights_input_hidden += (
(hidden_weights_change * eta) / sample_count
)
def batch_train(self, epoch_count, eta, patience=10):
"""Trains the network in batch mode. That means the weights
are updated after showing all training examples.
Eta is the learning rate and patience is the number of epochs
that the validation error is allowed to increase before
aborting.
"""
validation_error = self.measure_error(
self.validation_data, self.validation_data_solution
)
for epoch in range(epoch_count):
self.back_propagate(self.input_layer, self.output_layer, eta)
validation_error_new = self.measure_error(
self.validation_data, self.validation_data_solution
)
if validation_error_new < validation_error:
validation_error = validation_error_new
else:
patience -= 1
if patience == 0:
print(
'Abort Training. Overfitting has started!'
' Epoch: {0}. Error: {1}'.format(
epoch, validation_error_new
)
)
return
print('Epoch: {0}, Error: {1}'.format(epoch, validation_error))Ich hab' jetzt nur den Satz gelesen: das ist ein Float weil zumindest einer der Operanden ein Float ist, du kannst das Ergebnis aber ganz einfach via `int()` zu einem machen. `int(foo // 1)`. Was du aber wahrscheinlich wirklich suchst ist aber wahrscheinlich math.floor.nooby hat geschrieben://1 ist ist eine Floor Division und gibt einen float zurück. Ich benötige das Ergebnis aber als int. Soll ich das ganze anders programmieren?