输出方式

目录

• Outline
• y∈Rdy∈Rd
• yi∈[0,1]yi∈[0,1]
• yi∈[0,1],,∑ydi=0yi=1yi∈[0,1],,∑i=0ydyi=1
• yi∈[−1,1]yi∈[−1,1]

Outline

• y∈Rdy∈Rd

• 多分类一般为概率

• yi∈[0,1],i=0,1,⋯,yd−1yi∈[0,1],i=0,1,⋯,yd−1

• 多分类一般要求各个分类和为1

• yi∈[0,1],∑ydi=0yi=1,i=0,1,⋯,yd−1yi∈[0,1],∑i=0ydyi=1,i=0,1,⋯,yd−1

• yi∈[−1,1],i=0,1,⋯,yd−1yi∈[−1,1],i=0,1,⋯,yd−1

y∈Rdy∈Rd

• linear regression

• naive classification with MSE

• other general prediction

• out = relu(X@W + b)

  • logits

yi∈[0,1]yi∈[0,1]

• binary classfication

  • y>0.5,-->1
  • y<0.5,-->0

• Image Generation

  • rgb

• out = relu(X@W + b)

• sigmoid

f(x)=11+e−xf(x)=11+e−x

• out' = sigmoid(out) # 把输出值压缩在0-1

import tensorflow as tf

a = tf.linspace(-6., 6, 10)
a

<tf.Tensor: id=9, shape=(10,), dtype=float32, numpy=
array([-6.       , -4.6666665, -3.3333333, -2.       , -0.6666665,
        0.666667 ,  2.       ,  3.333334 ,  4.666667 ,  6.       ],
      dtype=float32)>

tf.sigmoid(a)

<tf.Tensor: id=21, shape=(10,), dtype=float32, numpy=
array([0.00247264, 0.00931591, 0.03444517, 0.11920291, 0.33924365,
       0.6607564 , 0.8807971 , 0.96555483, 0.99068403, 0.9975274 ],
      dtype=float32)>

x = tf.random.normal([1, 28, 28]) * 5
tf.reduce_min(x), tf.reduce_max(x)

(<tf.Tensor: id=49, shape=(), dtype=float32, numpy=-16.714912>,
 <tf.Tensor: id=51, shape=(), dtype=float32, numpy=16.983088>)

x = tf.sigmoid(x)
tf.reduce_min(x), tf.reduce_max(x)

(<tf.Tensor: id=56, shape=(), dtype=float32, numpy=8.940697e-08>,
 <tf.Tensor: id=58, shape=(), dtype=float32, numpy=1.0>)

yi∈[0,1],∑ydi=0yi=1yi∈[0,1],∑i=0ydyi=1

a = tf.linspace(-2., 2, 5)
tf.sigmoid(a)  # 输出值的和不为1

<tf.Tensor: id=73, shape=(5,), dtype=float32, numpy=
array([0.11920292, 0.26894143, 0.5       , 0.7310586 , 0.880797  ],
      dtype=float32)>

• softmax

tf.nn.softmax(a)  # 输出值的和为1

<tf.Tensor: id=67, shape=(5,), dtype=float32, numpy=
array([0.01165623, 0.03168492, 0.08612854, 0.23412165, 0.6364086 ],
      dtype=float32)>

logits = tf.random.uniform([1, 10], minval=-2, maxval=2)
logits

<tf.Tensor: id=81, shape=(1, 10), dtype=float32, numpy=
array([[ 1.988893  , -0.0625844 , -0.77338314, -1.1655569 , -1.8847818 ,
         1.3335037 ,  1.8299117 ,  0.8497076 , -0.15004253, -0.6530676 ]],
      dtype=float32)>

prob = tf.nn.softmax(logits, axis=1)
prob

<tf.Tensor: id=87, shape=(1, 10), dtype=float32, numpy=
array([[0.31882977, 0.04098393, 0.02013342, 0.01360187, 0.00662587,
        0.16554914, 0.2719657 , 0.10205092, 0.03755182, 0.02270753]],
      dtype=float32)>

tf.reduce_sum(prob, axis=1)

<tf.Tensor: id=85, shape=(1,), dtype=float32, numpy=array([1.], dtype=float32)>

yi∈[−1,1]yi∈[−1,1]

a

<tf.Tensor: id=72, shape=(5,), dtype=float32, numpy=array([-2., -1.,  0.,  1.,  2.], dtype=float32)>

tf.tanh(a)

<tf.Tensor: id=90, shape=(5,), dtype=float32, numpy=
array([-0.9640276, -0.7615942,  0.       ,  0.7615942,  0.9640276],
      dtype=float32)>