我使用标准化的MNIST数据集(输入要素= 784
)。我的网络架构是784-256-256-10
:两个隐藏的256个神经元层,每个神经元使用sigmoid激活函数,10个神经元输出层使用softmax激活。我也使用交叉熵成本函数。
权重矩阵初始化:
input_size=784
hidden1_size=256
hidden2_size=256
output_size=10
Theta1 = np.random.randn(hidden1_size, input_size)
b1 = np.random.randn(hidden1_size)
Theta2 = np.random.randn(hidden2_size, hidden1_size)
b2 = np.random.randn(hidden2_size)
Theta3 = np.random.randn(output_size, hidden2_size)
b3 = np.random.randn(output_size)
我的网络按预期工作:
epochs = 2000
learning_rate = 0.01
for j in range(epochs):
# total_train is an array of length 50000
# Each element of total_train is a tuple of: (a) input vector of length 784
# and (b) the corresponding one-hot encoded label of length 10
# Similarly, total_test is an array of length 10000
shuffle(total_train)
train = total_train[:1000]
shuffle(total_test)
test = total_test[:1000]
predictions = []
test_predictions = []
for i in range(len(train)):
# Feed forward
x, t = train[i][0], train[i][1]
z1 = np.dot(Theta1, x) + b1
a1 = sigmoid(z1)
z2 = np.dot(Theta2, a1) + b2
a2 = sigmoid(z2)
z3 = np.dot(Theta3, a2) + b3
y = softmax(z3)
# Is prediction == target?
predictions.append(np.argmax(y) == np.argmax(t))
# Negative log probability cost function
cost = -t * np.log(y)
# Backpropagation
delta3 = (y - t) * softmax_prime(z3)
dTheta3 = np.outer(delta3, a2)
db3 = delta3
delta2 = np.dot(Theta3.T, delta3) * sigmoid_prime(z2)
dTheta2 = np.outer(delta2, a1)
db2 = delta2
delta1 = np.dot(Theta2.T, delta2) * sigmoid_prime(z1)
dTheta1 = np.outer(delta1, x)
db1 = delta1
# Update weights
Theta1 -= learning_rate * dTheta1
b1 -= learning_rate * db1
Theta2 -= learning_rate * dTheta2
b2 -= learning_rate * db2
Theta3 -= learning_rate * dTheta3
b3 -= learning_rate * db3
if j % 10 == 0:
m = len(predictions)
performance = sum(predictions)/m
print('Epoch:', j, 'Train performance:', performance)
# Test accuracy on test data
for i in range(len(test)):
# Feed forward
x, t = test[i][0], test[i][1]
z1 = np.dot(Theta1, x) + b1
a1 = sigmoid(z1)
z2 = np.dot(Theta2, a1) + b2
a2 = sigmoid(z2)
z3 = np.dot(Theta3, a2) + b3
y = softmax(z3)
# Is prediction == target?
test_predictions.append(np.argmax(y) == np.argmax(t))
m = len(test_predictions)
performance = sum(test_predictions)/m
print('Epoch:', j, 'Test performance:', performance)
输出(每10个时期):
Epoch: 0 Train performance: 0.121
Epoch: 0 Test performance: 0.146
Epoch: 10 Train performance: 0.37
Epoch: 10 Test performance: 0.359
Epoch: 20 Train performance: 0.41
Epoch: 20 Test performance: 0.433
Epoch: 30 Train performance: 0.534
Epoch: 30 Test performance: 0.52
Epoch: 40 Train performance: 0.607
Epoch: 40 Test performance: 0.601
Epoch: 50 Train performance: 0.651
Epoch: 50 Test performance: 0.669
Epoch: 60 Train performance: 0.71
Epoch: 60 Test performance: 0.711
Epoch: 70 Train performance: 0.719
Epoch: 70 Test performance: 0.694
Epoch: 80 Train performance: 0.75
Epoch: 80 Test performance: 0.752
Epoch: 90 Train performance: 0.76
Epoch: 90 Test performance: 0.758
Epoch: 100 Train performance: 0.766
Epoch: 100 Test performance: 0.769
但是当我介绍 Dropout 正规化方案时,我的网络中断了。我的辍学代码更新是:
dropout_prob = 0.5
# Feed forward
x, t = train[i][0], train[i][1]
z1 = np.dot(Theta1, x) + b1
a1 = sigmoid(z1)
mask1 = np.random.random(len(z1))
mask1 = mask1 < dropout_prob
a1 *= mask1
z2 = np.dot(Theta2, a1) + b2
a2 = sigmoid(z2)
mask2 = np.random.random(len(z2))
mask2 = mask2 < dropout_prob
a2 *= mask2
z3 = np.dot(Theta3, a2) + b3
y = softmax(z3)
# Backpropagation
delta3 = (y - t) * softmax_prime(z3)
dTheta3 = np.outer(delta3, a2)
db3 = delta3 * 1
delta2 = np.dot(Theta3.T, delta3) * sigmoid_prime(z2)
dTheta2 = np.outer(delta2, a1)
db2 = delta2 * 1
delta1 = np.dot(Theta2.T, delta2) * sigmoid_prime(z1)
dTheta1 = np.outer(delta1, x)
db1 = delta1 * 1
表现保持在0.1
(10%)左右。
非常感谢任何关于我出错的地方。
答案 0 :(得分:0)
您的辍学实施存在一个主要问题,因为您在测试时间没有缩放激活。这是great CS231n tutorial:
的引用至关重要的是,请注意
predict
函数中我们不再删除,但我们正在p
执行两个隐藏图层输出的缩放。这很重要,因为在测试时,所有神经元都会看到它们的全部 输入,所以我们希望在测试时神经元的输出是相同的 在培训时间达到预期产出。例如,在的情况下
p=0.5
,神经元必须在测试时将其输出减半 与训练期间(预期)相同的输出。要看到这一点,请考虑神经元
x
的输出(在丢失之前)。同 辍学,这个神经元的预期输出将成为px+(1−p)0
,因为神经元的输出将设置为零 概率1−p
。在测试时,我们始终保持神经元 我们必须调整x→px
以保持相同的预期输出。还可以证明在测试时执行此衰减可以 与迭代所有可能的二进制掩码的过程有关 (因此所有指数级的子网络)和计算 他们的集合预测。
最常见的解决方案是使用反向压差,它在列车时执行缩放,在测试时保持正向传递不变。这就是它在代码中的样子:
mask1 = (mask1 < dropout_prob) / dropout_prob
...
mask2 = (mask2 < dropout_prob) / dropout_prob
...