目录

• Outline
• Reduce Dim
• subsample
  • Max/Avg pooling
  • Strides
  • For instance
• upsample
  • UpSampling2D
• ReLu

Outline

• Pooling

  SRE实战 互联网时代守护先锋，助力企业售后服务体系运筹帷幄！一键直达领取阿里云限量特价优惠。

• upsample

• ReLU

Reduce Dim

subsample

Max/Avg pooling

• stride = 2

Strides

• stride = 1

For instance

import tensorflow as tf
from tensorflow.keras import layers

x = tf.random.normal([1, 14, 14, 4])
x.shape

TensorShape([1, 14, 14, 4])

pool = layers.MaxPool2D(2, strides=2)
out = pool(x)
out.shape

TensorShape([1, 7, 7, 4])

pool = layers.MaxPool2D(3, strides=2)
out = pool(x)
out.shape

TensorShape([1, 6, 6, 4])

out = tf.nn.max_pool2d(x, 2, strides=2, padding='VALID')
out.shape

TensorShape([1, 7, 7, 4])

upsample

• nearest

• bilinear

UpSampling2D

x = tf.random.normal([1, 7, 7, 4])
x.shape

TensorShape([1, 7, 7, 4])

layer = layers.UpSampling2D(size=3)
out = layer(x)
out.shape

TensorShape([1, 21, 21, 4])

layer = layers.UpSampling2D(size=2)
out = layer(x)
out.shape

TensorShape([1, 14, 14, 4])

ReLu

x = tf.random.normal([2,3])
x

<tf.Tensor: id=76, shape=(2, 3), dtype=float32, numpy=
array([[-0.30181265,  0.39785287, -0.78380096],
       [ 0.6593401 , -0.40962896, -0.3656048 ]], dtype=float32)>

tf.nn.relu(x)
x

<tf.Tensor: id=76, shape=(2, 3), dtype=float32, numpy=
array([[-0.30181265,  0.39785287, -0.78380096],
       [ 0.6593401 , -0.40962896, -0.3656048 ]], dtype=float32)>

layers.ReLU()(x)

<tf.Tensor: id=80, shape=(2, 3), dtype=float32, numpy=
array([[0.        , 0.39785287, 0.        ],
       [0.6593401 , 0.        , 0.        ]], dtype=float32)>

扫码关注我们

微信号：SRE实战

拒绝背锅 运筹帷幄