python 相关的知识和笔记链接

接受不定参数

def add(x, *args):
    total = x
    for arg in args:
        total += arg
    return total

这里，*args 表示参数数目不定，可以看成一个元组，把第一个参数后面的参数当作元组中的元素。

print(add(1, 2, 3, 4))
print(add(1, 2))
----
>>>10
>>>3

def add(x, **kwargs):
    total = x
    for arg, value in kwargs.items():
        print "adding ", arg
        total += value
    return total

这里， **kwargs 表示参数数目不定，相当于一个字典，关键词和值对应于键值对。

print add(10, y=11, z=12, w=13)
----
>>> adding  y
>>> adding  z
>>> adding  w
>>> 46

def foo(*args, **kwargs):
    print args, kwargs

foo(2, 3, x='bar', z=10)
-----
>>> (2, 3) {'x': 'bar', 'z': 10}

tf 里面的training=True

Some neural network layers behave differently during training and inference, for example Dropout and BatchNormalization layers. For example

During training, dropout will randomly drop out units and correspondingly scale up activations of the remaining units.
During inference, it does nothing (since you usually don’t want the randomness of dropping out units here).

The training argument lets the layer know which of the two “paths” it should take. If you set this incorrectly, your network might not behave as expected.

pycharm的奇技淫巧

https://www.zhihu.com/question/37787004

为什么要做归一化处理

https://mp.weixin.qq.com/s/TF6d9NRz0lDFQeC_K3CVaw

npy 格式的好处

https://towardsdatascience.com/what-is-npy-files-and-why-you-should-use-them-603373c78883

不用reshape了，什么格式保存，什么格式读取
storage比较小
Read的速度比较快

pickle data

https://www.geeksforgeeks.org/understanding-python-pickling-example/

https://www.zhihu.com/search?type=content&q=Pickling

答：Pickle模块读入任何Python对象，将它们转换成字符串，然后使用dump函数将其转储到一个文件中——这个过程叫做pickling。反之从存储的字符串文件中提取原始Python对象的过程，叫做unpickling。 allow_pickle = True文件传输的过程中可能会有压缩，true则表示压缩后文件不变

Python的面试

https://zhuanlan.zhihu.com/p/41962762

1.这两个参数是什么意思:*args,\kwargs？我们为什么要使用它们?**

答:如果我们不确定往一个函数中传入多少参数，或者我们希望以元组(tuple)或者列表(list)的形式传参数的时候，我们可以使用*args(单星号).如果我们不知道往函数中传递多少个关键词参数或者想传入字典的值作为关键词参数的时候我们可以使用**kwargs(双星号),args,kwargs两个标识符是约定俗成的用法。

lists are mutable while tuple are not

这个就非常的好，解释kargs and args

https://realpython.com/python-kwargs-and-args/

https://www.jianshu.com/p/592cf526b1e6

https://www.scaler.com/topics/python/args-and-kwargs-in-python/

https://wiingy.com/learn/python/args-and-kwargs-in-python/

Python 的iteration 这个模块的用法

https://www.zhihu.com/search?type=content&q=itertools

Itertools.zip_longest()

This iterator falls under the category of Terminating Iterators. It prints the values of iterables alternatively in sequence. If one of the iterables is printed fully, the remaining values are filled by the values assigned to fillvalue parameter.

Python新手常见的坑

https://zhuanlan.zhihu.com/p/81012511

Tf.function 装饰器的玩意

func	the function to be compiled. If func is None, tf.function returns a decorator that can be invoked with a single argument - func. In other words, tf.function(input_signature=…)(func) is equivalent to tf.function(func, input_signature=…). The former can be used as decorator.
input_signature	A possibly nested sequence of tf.TensorSpec objects specifying the shapes and dtypes of the Tensors that will be supplied to this function. If None, a separate function is instantiated for each inferred input signature. If input_signature is specified, every input to func must be a Tensor, and func cannot accept **kwargs.

tf graph：

Graphs are data structures that contain a set of tf.Operation objects, which represent units of computation; and tf.Tensor objects, which represent the units of data that flow between operations. They are defined in a tf.Graph context. Since these graphs are data structures, they can be saved, run, and restored all without the original Python code.

permutation invariant

In this context this refers to the fact that the model does not assume any spatial relationships between the features. E.g. for multilayer perceptron, you can permute the pixels and the performance would be the same. This is not the case for convolutional networks, which assume neighbourhood relations.

numpy -1 的作用

https://stackoverflow.com/questions/tagged/numpy-ndarray

Tensorflow.Dataset中map，shuffle，repeat，batch的总结

https://blog.csdn.net/anshuai_aw1/article/details/105094548

shuffle的顺序很重要，应该先shuffle再batch，如果先batch后shuffle的话，那么此时就只是对batch进行shuffle，而batch里面的数据顺序依旧是有序的，那么随机程度会减弱

buffer_size 越大，打乱的程度越高

https://www.cnblogs.com/HolyShine/p/8673322.html

数据集的处理和预处理，非常重要

https://tf.wiki/zh_hans/basic/tools.html#zh-hans-tfdata

Tensorflow Dataset API 用法

https://zhuanlan.zhihu.com/p/30751039

Tensorflow 数据读取机制