我想要通过矩阵乘法手动计算Keras模型的输出结果。我希望这样做可以帮助我更好地理解Keras的工作原理。我将使用简单的XOR问题进行演示。以下是我的代码:
import numpy as np
import keras
from keras.models import Sequential
from keras.layers.core import Dense
from keras.callbacks import LambdaCallback
class LossHistory(keras.callbacks.Callback):
def on_train_begin(self, logs={}):
self.losses = []
def on_batch_end(self, batch, logs={}):
self.losses.append(logs.get('loss'))
history = LossHistory()
# the four different states of the XOR gate
training_data = np.array([[0,0],[0,1],[1,0],[1,1]], "float32")
# the four expected results in the same order
target_data = np.array([[0],[1],[1],[0]], "float32")
model = Sequential()
model.add(Dense(4, input_dim=2, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print_weights = LambdaCallback(on_epoch_end=lambda batch, logs: print(model.layers[0].get_weights()))
model.compile(loss='mean_squared_error',
optimizer='adam',
metrics=['binary_accuracy'])
history2 = model.fit(training_data, target_data, epochs=50, verbose=2, callbacks=[print_weights, history])
print(model.predict(training_data).round())
W1 = model.get_weights()[0]
X1 = np.matrix([[0,0],[1,1]], "float32")
wx = np.dot(X1,W1)
b = model.get_weights()[1]
wx = np.reshape(wx,(4,2))
b = np.reshape(b, (4,1))
z = wx + b
from numpy import array, exp
a1 = 1 / (1 + exp(-z))
print('g =\n', a1)
W2 = model.get_weights()[2]
b2 = model.get_weights()[3]
W2 = np.reshape(W2,(1,4))
a1 = np.reshape(a1, (4,1))
wa = np.dot(W2,a1)
z2 = wa + b2
a2 = 1 / (1 + exp(-z2))
print('g =\n', a2)
据我所了解,
get_weights()[0]
和get_weights()[1]
分别是第一层的权重和偏置,get_weights()[2]
和get_weights()[3]
是第二层的权重和偏置。我认为我的问题在于找出x1和x2与方程z = Wx + b的关系。这些权重是从最后一个时期中检索出来的,通常是实现100%准确度的权重。我期望的输出是[0,1,1,0],基于手动计算z = Wx + b并对z取sigmoid得到y-hat预测值。