def classify(self, testInstance):
"""Classify a single instance.
Parameters
----------
testInstance : list of floats
Returns
-------
bool :
True if the testInstance is recognized as a 7, False otherwise.
"""
# Write your code to do the classification on an input image
return Activation.sign(np.dot(testInstance, self.weight))
def train(self, verbose=True):
"""Train the perceptron with the perceptron learning algorithm.
Parameters
----------
verbose : boolean
Print logging messages with validation accuracy if verbose is True.
"""
# Write your code to train the perceptron here
pass
for epoch in range(self.epochs):
for i in range(self.trainingSet.input.shape[0]):
pre_result = dot(self.weight, self.trainingSet.input[i, :])
result = Activation.sign(pre_result, threshold=0)
error = self.trainingSet.label[i] - result
self.updateWeights(self.trainingSet.input[i, :], error)
correct = 0.0
for j in range(self.validationSet.input.shape[0]):
valid_result = Activation.sign(
dot(self.weight, self.validationSet.input[j, :]))
if valid_result == self.validationSet.label[j]:
correct += 1.0
accuracy = correct / self.validationSet.input.shape[0]
# print('after %d times training, valiation accuracy : %.4f %d' %(epoch, accuracy, correct))
# Den Schwellwert hab ich selbst auf 0.98 gesetzt
if accuracy >= 0.98:
if verbose:
print(
'After %d times training, Validation accuracy:%.4f>0.98'
% (epoch, accuracy))
print('Stop training to avoid overfitting!')
break
if epoch == self.epochs - 1:
print(
'No accuracy >= threshold, no need to break loop to avoid overfitting'
)
def classify(self, testInstance):
"""Classify a single instance.
Parameters
----------
testInstance : list of floats
Returns
-------
bool :
True if the testInstance is recognized as a 7, False otherwise.
"""
# Write your code to do the classification on an input image
pass
testResult = Activation.sign(dot(self.weight, testInstance),
threshold=0)
return testResult
def fire(self, input):
"""Fire the output of the perceptron corresponding to the input """
return Activation.sign(np.dot(np.array(input), self.weight))
def fire(self, input):
"""Fire the output of the perceptron corresponding to the input """
return Activation.sign(np.dot(np.array(input), self.weight))
def fire(self, input):
"""Fire the output of the perceptron corresponding to the input """
# I already implemented it for you to see how you can work with numpy
return Activation.sign(np.dot(np.array(input), self.weight[1:]) + self.weight[0])
def _fire(self, input):
"""Fire the output of the perceptron corresponding to the input """
# I already implemented it for you to see how you can work with numpy
return Activation.sign(np.dot(np.array(input), self.weight))
