如何在Python中实现softmax反向传播。

import torchimport mathdef my_softmax(features):    _sum = 0    for i in features:        _sum += math.e ** i    return torch.Tensor([ math.e ** i / _sum for i in features ])def my_softmax_grad(outputs):        n = len(outputs)    grad = []    for i in range(n):        temp = []        for j in range(n):            if i == j:                temp.append(outputs[i] * (1- outputs[i]))            else:                temp.append(-outputs[j] * outputs[i])        grad.append(torch.Tensor(temp))    return gradif __name__ == '__main__':    features = torch.randn(10)    features.requires_grad_()    torch_softmax = torch.nn.functional.softmax    p1 = torch_softmax(features,dim=0)    p2 = my_softmax(features)    print(torch.allclose(p1,p2))        n = len(p1)    p2_grad = my_softmax_grad(p2)    for i in range(n):        p1_grad = torch.autograd.grad(p1[i],features, retain_graph=True)        print(torch.allclose(p1_grad[0], p2_grad[i]))