Question

我正在用python学习机器学习。这段代码来自Standford Uiv类。我试图掌握这些代码，但失败了。

问题是loss_W = lambda W: self.loss(x,t)。是不是真的，loss_W（1）或loss_W（2）或任何东西都不能改变结果？

我无法理解这两个代码的结果是不同的。

grads['W1'] = numerical_gradient(loss_W, self.params['W1']) 

grads['b1'] = numerical_gradient(loss_W, self.params['b1'])


def numerical_gradient(f, x):

    h = 1e-4 # 0.0001
    grad = np.zeros_like(x) 

    for idx in range(x.size):
        tmp_val = x[idx]

        # f(x+h) 
        x[idx] = float(tmp_val) + h
        fxh1 = f(x)

        # f(x-h) 
        x[idx] = tmp_val - h 
        fxh2 = f(x) 

        grad[idx] = (fxh1 - fxh2) / (2*h)
        x[idx] = tmp_val 

    return grad

class TwoLayerNet:

    def __init__(self, input_size, hidden_size, output_size, weight_init_std=0.01):
        self.params = {}
        self.params['W1'] = weight_init_std * np.random.randn(input_size, hidden_size)
        self.params['b1'] = np.zeros(hidden_size)
        self.params['W2'] = weight_init_std * np.random.randn(hidden_size, output_size)
        self.params['b2'] = np.zeros(output_size)

    def predict(self, x):
        W1, W2 = self.params['W1'], self.params['W2']
        b1, b2 = self.params['b1'], self.params['b2']

        a1 = np.dot(x, W1)
        z1 = sigmoid(a1)
        a2 = np.dot(z1,W2)
        y = softmax(a2)

        return y

    def loss(self, x, t):
        y = self.predict(x)
        return cross_entropy_error(y,t)

    def accuracy(self, x,t):
        y = self.predict(x)
        y = np.argmax(y, axis=0)
        t = np.argmax(t, axis=0)
        data_len = len(x)
        accuracy = np.sum(y==t)/float(data_len)
        return accuracy

    def numerical_gradient(self, x, t):
        loss_W = lambda W: self.loss(x,t)

        grads = {}
        grads['W1'] = numerical_gradient(loss_W, self.params['W1'])
        grads['b1'] = numerical_gradient(loss_W, self.params['b1'])
        grads['W2'] = numerical_gradient(loss_W, self.params['W2'])
        grads['b2'] = numerical_gradient(loss_W, self.params['b2'])

        return grads

Answer 1

单独的lambda loss_W = lambda W: self.loss(x,t)与W的值无关。这个功能可以像这样简化：

x = 1 # Just some random value
t = 5 # Just some random value

def simplified_lambda_function(W):
    return (x,t)

您发布的代码段表示某处的类定义为

grads['W1'] = numerical_gradient(loss_W, self.params['W1']) 

grads['b1'] = numerical_gradient(loss_W, self.params['b1']

self在这里未定义。因此，我们无法确定它们是否真的相同，但很可能是它们。

我无法理解这个lambda函数

1 个答案: