np.argmax() 函数:获取最大元素的索引
axis=1 ,代表沿着第一维方向
array([[0.1, 0.8, 0.1],
[0.3, 0.1, 0.6],
[0.2, 0.5, 0.3],
[0.8, 0.1, 0.1]])
>>> y=np.argmax(x,axis=1)
Traceback (most recent call last):
File "<pyshell#3>", line 1, in <module>
y=np.argmax(x,axis=1)
NameError: name 'x' is not defined
>>> x=np.argmax(y,axis=1)
>>> x
array([1, 2, 1, 0], dtype=int64)
>>>
np.dot(),求乘积的函数
>>> x
array([2, 1, 2, 3, 2, 0, 1, 0])
>>> x=np.random.rand(2)
>>> x
array([0.00648089, 0.17369308])
>>> w=np.random.rand(2)
>>> w
array([0.31616868, 0.17482418])
>>> w=np.random.rand(2,3)
>>> w
array([[0.35726823, 0.62343659, 0.18229093],
[0.27851121, 0.90234157, 0.64444163]])
>>> b=np.random.rand(3)
>>> b
array([0.62218577, 0.59356922, 0.40364196])
>>> x.shape()
Traceback (most recent call last):
File "<pyshell#18>", line 1, in <module>
x.shape()
TypeError: 'tuple' object is not callable
>>> x.shape
(2,)
>>> y=np.dot(x,w)+b
>>> y
array([0.67287666, 0.75434013, 0.51675842])
>>>