class MLP:
def __init__(self, input_size, hidden_size_1, hidden_size_2, output_size):
self.input_layer = InputLayer(input_size, hidden_size_1, ReLU)
self.hidden_layer = HiddenLayer(hidden_size_1, hidden_size_2)
self.output_layer = SoftmaxOutputLayer(hidden_size_2, output_size)
def predict(self, x):
x = self.input_layer.forward(x)
x = self.hidden_layer.forward(x)
prob = self.output_layer.predict(x)
pred = np.argmax(prob, axis=-1)
return pred
def loss(self, x, y):
x = self.input_layer.forward(x)
x = self.hidden_layer.forward(x)
loss = self.output_layer.forward(x, y)
return loss
def gradient(self):
d_prev = 1
d_prev = self.output_layer.backward(d_prev=d_prev)
d_prev = self.hidden_layer.backward(d_prev)
self.input_layer.backward(d_prev)
def update(self, learning_rate):
self.input_layer.W -= self.input_layer.dW * learning_rate
self.input_layer.b -= self.input_layer.db * learning_rate
self.hidden_layer.W -= self.hidden_layer.dW * learning_rate
self.hidden_layer.b -= self.hidden_layer.db * learning_rate
self.output_layer.W -= self.output_layer.dW * learning_rate
self.output_layer.b -= self.output_layer.db * learning_rate
class MLP:
def __init__(self, input_size, hidden_size, output_size):
self.input_layer = InputLayer(input_size, hidden_size, Sigmoid)
self.output_layer = SigmoidOutputLayer(hidden_size, output_size)
def predict(self, x):
x = self.input_layer.forward(x)
pred = self.output_layer.predict(x)
pred[pred >= 0.5] = 1
pred[pred < 0.5] = 0
return pred
def loss(self, x, y):
x = self.input_layer.forward(x)
loss = self.output_layer.forward(x, y)
return loss
def gradient(self):
d_prev = 1
d_prev = self.output_layer.backward(d_prev=d_prev)
self.input_layer.backward(d_prev)
def update(self, learning_rate):
self.input_layer.W -= self.input_layer.dW * learning_rate
self.input_layer.b -= self.input_layer.db * learning_rate
self.output_layer.W -= self.output_layer.dW * learning_rate
self.output_layer.b -= self.output_layer.db * learning_rate
def __init__(self, input_size, hidden_size_1, hidden_size_2, output_size):
self.input_layer = InputLayer(input_size, hidden_size_1, ReLU)
self.hidden_layer = HiddenLayer(hidden_size_1, hidden_size_2)
self.output_layer = SoftmaxOutputLayer(hidden_size_2, output_size)
"""
The results should be exactly same as below:
결과는 아래와 일치해야 합니다:
Forward:
[[1.69405863 0. ]
[1.41846232 0. ]]
dW:
[[ 1. 0.]
[-3. 0.]
[-2. 0.]]
db:
[-1. 0.]
"""
input_layer = InputLayer(3, 2, ReLU)
input_layer.w = np.array([[1.0, -2.0], [2.0, -1.0], [-3.5, -0.5]])
input_layer.b = np.array([1.0, -1.0])
temp6 = np.array([[-1, 3, 2], [0.0, 1.0, 0.0]])
temp7 = np.array([[-1, 3], [0.0, 1.0]])
print('Forward: \n', input_layer.forward(temp6))
input_layer.backward(temp7)
print('dW: \n', input_layer.dW)
print('db: \n', input_layer.db)
print()
print('===== HiddenLayer Check =====')
"""
The results should be exactly same as below:
결과는 아래와 일치해야 합니다:
def __init__(self, input_size, hidden_size, output_size):
self.input_layer = InputLayer(input_size, hidden_size, Sigmoid)
self.output_layer = SigmoidOutputLayer(hidden_size, output_size)