目录

* Outline <https://www.cnblogs.com/nickchen121/p/10930571.html#outline>
* Reduce Dim <https://www.cnblogs.com/nickchen121/p/10930571.html#reduce-dim>
* subsample <https://www.cnblogs.com/nickchen121/p/10930571.html#subsample>
* Max/Avg pooling
<https://www.cnblogs.com/nickchen121/p/10930571.html#maxavg-pooling>
* Strides <https://www.cnblogs.com/nickchen121/p/10930571.html#strides>
* For instance
<https://www.cnblogs.com/nickchen121/p/10930571.html#for-instance>
* upsample <https://www.cnblogs.com/nickchen121/p/10930571.html#upsample>
* UpSampling2D
<https://www.cnblogs.com/nickchen121/p/10930571.html#upsampling2d>
* ReLu <https://www.cnblogs.com/nickchen121/p/10930571.html#relu>
Outline

*
Pooling

*
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)>

友情链接
KaDraw流程图
API参考文档
OK工具箱
云服务器优惠
阿里云优惠券
腾讯云优惠券
华为云优惠券
站点信息
问题反馈
邮箱:[email protected]
QQ群:637538335
关注微信