使用多个隐藏层时神经网络的准确性非常差

我创建了以下神经网络：

def init_weights(m, n=1):
"""
initialize a matrix/vector of weights with xavier initialization
:param m: out dim
:param n: in dim
:return: matrix/vector of random weights
"""
limit = (6 / (n * m)) ** 0.5
weights = np.random.uniform(-limit, limit, size=(m, n))
if n == 1:
weights = weights.reshape((-1,))
return weights
def softmax(v):
exp = np.exp(v)
return exp / np.tile(exp.sum(1), (v.shape[1], 1)).T
def relu(x):
return np.maximum(x, 0)
def sign(x):
return (x > 0).astype(int)
class Model:
"""
A class for neural network model
"""
def __init__(self, sizes, lr):
self.lr = lr
self.weights = []
self.biases = []
self.memory = []
for i in range(len(sizes) - 1):
self.weights.append(init_weights(sizes[i + 1], sizes[i]))
self.biases.append(init_weights(sizes[i + 1]))
def forward(self, X):
self.memory = [X]
X = np.dot(self.weights[0], X.T).T + self.biases[0]
for W, b in zip(self.weights[1:], self.biases[1:]):
X = relu(X)
self.memory.append(X)
X = np.dot(W, X.T).T + b
return softmax(X)
def backward(self, y, y_pred):
# calculate the errors for each layer
y = np.eye(y_pred.shape[1])[y]
errors = [y_pred - y]
for i in range(len(self.weights) - 1, 0, -1):
new_err = sign(self.memory[i]) *
np.dot(errors[0], self.weights[i])
errors.insert(0, new_err)

# update weights
for i in range(len(self.weights)):
self.weights[i] -= self.lr *
np.dot(self.memory[i].T, errors[i]).T
self.biases[i] -= self.lr * errors[i].sum(0)


数据有10个类。当使用单个隐藏层时，准确率几乎为 40%。当使用 2 或 3 个隐藏层时，准确率大约是第一个 epoch 的 9-10%，并且仍然如此。训练集上的准确率也在这个范围内。我的实现是否存在可能导致这种情况的问题？