如何计算RNN和LSTM的参数数量？

Environment:

python version: 3.7.4
pip version: 19.0.3
numpy version:1.19.4
matplotlib version:3.3.3
tensorflow version:1.14.0
keras version:2.1.5

代码如下:

from keras.layers import SimpleRNN
from keras.models import Model
from keras  import Input

inputs = Input((None, 5))
simple_rnn = SimpleRNN(4)

output = simple_rnn(inputs)  # The output has shape `[32, 4]`.
model = Model(inputs,output)
model.summary()

Output:

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_4 (InputLayer)         (None, None, 5)           0         
_________________________________________________________________
simple_rnn_1 (SimpleRNN)     (None, 4)                 40        
=================================================================
Total params: 40
Trainable params: 40
Non-trainable params: 0
_________________________________________________________________

这里的simple_rnn_1中的param为40是怎么计算的呢？

创建一个简单的RNN网络

Environment:

python version: 3.7.4
pip version: 19.0.3
numpy version:1.19.4
matplotlib version:3.3.3
tensorflow version:1.14.0
keras version:2.1.5

代码如下：

import keras
from keras import backend as K
from keras.layers import RNN
class MinimalRNNCell(keras.layers.Layer):

	def __init__(self, units,use_bias = True, **kwargs):
		self.units = units
		self.state_size = units
		self.use_bias = use_bias
		super(MinimalRNNCell, self).__init__(**kwargs)

	def build(self, input_shape):
		self.kernel = self.add_weight(shape=(input_shape[-1], self.units), # 添加kernel
										initializer='uniform',
										name='kernel')
		self.recurrent_kernel = self.add_weight(# 添加循环层kernel
			shape=(self.units, self.units),
			initializer='uniform',
			name='recurrent_kernel')

		if self.use_bias:
			self.bias = self.add_weight( # 添加bias
				shape=(self.units,),
				name='bias',
				initializer='uniform',)
		else:
			self.bias = None

		self.built = True

	def call(self, inputs, states):
		prev_output = states[0]
		h = K.dot(inputs, self.kernel)
		output = h + K.dot(prev_output, self.recurrent_kernel)
		return output, [output]


# Let's use this cell in a RNN layer:

cell = MinimalRNNCell(32)
x = keras.Input((None, 5))
layer = RNN(cell)
y = layer(x)

model = keras.Model(x,y)
model.summary()

Output:

Config Github with SSH

Generating a new SSH key

1.Open TerminalTerminalGit Bash.

2.Paste the text below, substituting in your GitHub email address.

$ ssh-keygen -t ed25519 -C "your_email@example.com"

3.Then you’re prompted to do something, press Enter.

Then the keys will be saved under ~/.ssh folder.

You can use ls -al ~/.ssh command to see them.

LOG:

$ ssh-keygen -t ed25519 -C "my_email@example.com"
Generating public/private ed25519 key pair.
Enter file in which to save the key (/c/Users/myusername/.ssh/id_ed25519):
Enter passphrase (empty for no passphrase):
Enter same passphrase again:
Your identification has been saved in /c/Users/myusername/.ssh/id_ed25519.
Your public key has been saved in /c/Users/myusername/.ssh/id_ed25519.pub.

Config github key

Copy gitbash:

Telnet

telnet host post

示例：

[yaohong@host ~]# telnet www.baidu.com 80
Trying 14.215.177.38...
Connected to www.baidu.com.
Escape character is '^]'.

出现Connected to表示连接上主机；

[yaohong@host ~]# telnet www.baidu.com 882
Trying 14.215.177.38...
telnet: connect to address 14.215.177.38: Connection timed out
Trying 14.215.177.39...

没有出现Connected to表示未连接成功。

如何计算一个BatchNormalization的参数？

# Environment：
# OS			macOS Catalina 10.15.6
# python 		3.7
# pip 			20.1.1
# tensorflow	1.14.0
# Keras 		2.1.5

from keras.models import Sequential
from keras.layers import Conv2D,BatchNormalization
model = Sequential();
# conv2d + max pooling
model.add(
	Conv2D(96, 
		kernel_size = (11,11), 
		strides=(4, 4), 
		padding="valid", 
		input_shape=(224,224,3),
		activation="relu")
	); # output  55 * 55 * 96 

# batchNormalization ! 
model.add(BatchNormalization()) # output
model.summary();

output:

双线插值是什么？

图像处理中，有时我们需要放大图片，比如原来图片宽高是300*300px，如果要在500*500的屏幕上展示，这时一种方法就是把图片直接拉大到500*500，但会发现图像变得模糊了，有没有什么办法可以放大图像而又不会让图像过于模糊呢？

Understanding limits to infinity

When x->∞, what is the exact number of x?

We don’t know, x is undefined.

∞ is not a number, is a idea of having a greater number than you give.

When x->∞, 1/x appoachs zero, but is never equal zero!

When n -> ∞, does sin(1/n) / (1/n) have meaning?

I used to thought 1/n = 0 while n->∞, but 0 cannot be divided, So I was confused.