标签：ima 提取 div down 神经元 and oat 思路 pre
bestloss = float(‘inf‘) # 无穷大
for num in range(1000):
W = np.random.randn(10, 3073) * 0.0001
loss = L(X_train, Y_train, W)
if loss < bestloss:
bestloss = loss
bestW = W
scores = bsetW.dot(Xte_cols)
Yte_predict = np.argmax(score, axis = 0)
np.mean(Yte_predict == Yte)
核心思路：迭代优化
W = np.random.randn(10, 3073) * 0.001
bestloss = float(‘inf‘)
for i in range(1000):
step_size = 0.0001
Wtry = np.random.randn(10, 3073) * step_size
loss = L(Xtr_cols, Ytr, Wtry)
if loss < bestloss:
W = Wtry
bestloss = loss
a 0,0,0,1
b 0,0,1,0
c 0,1,0,0
d 1,0,0,0
这样
下面的代码理论上输出1.0,实际输出0.95,也就是说在数值偏大的时候计算会不准
a = 10**9
for i in range(10**6):
a = a + 1e-6
print (a - 10**9)
# 0.95367431640625
所以会有优化初始数据的过程，最好使均值为0,方差相同：
以红色通道为例：(R-128）/128
标签：ima 提取 div down 神经元 and oat 思路 pre
原文地址：http://www.cnblogs.com/hellcat/p/6986201.html
