zoukankan      html  css  js  c++  java
  • Making training mini-batches

    Here is where we'll make our mini-batches for training. Remember that we want our batches to be multiple sequences of some desired number of sequence steps. Considering a simple example, our batches would look like this:

    We have our text encoded as integers as one long array in encoded. Let's create a function that will give us an iterator for our batches. I like using generator functions to do this. Then we can pass encoded into this function and get our batch generator.

    The first thing we need to do is discard some of the text so we only have completely full batches. Each batch contains N×MN×M characters, where NN is the batch size (the number of sequences) and MM is the number of steps. Then, to get the number of batches we can make from some array arr, you divide the length of arr by the batch size. Once you know the number of batches and the batch size, you can get the total number of characters to keep.

    After that, we need to split arr into NN sequences. You can do this using arr.reshape(size) where size is a tuple containing the dimensions sizes of the reshaped array. We know we want NN sequences (n_seqs below), let's make that the size of the first dimension. For the second dimension, you can use -1 as a placeholder in the size, it'll fill up the array with the appropriate data for you. After this, you should have an array that is N×(MK)N×(M∗K) where KK is the number of batches.

    Now that we have this array, we can iterate through it to get our batches. The idea is each batch is a N×MN×M window on the array. For each subsequent batch, the window moves over by n_steps. We also want to create both the input and target arrays. Remember that the targets are the inputs shifted over one character. You'll usually see the first input character used as the last target character, so something like this:

    y[:, :-1], y[:, -1] = x[:, 1:], x[:, 0]
    

    where x is the input batch and y is the target batch.

    The way I like to do this window is use range to take steps of size n_steps from 00 to arr.shape[1], the total number of steps in each sequence. That way, the integers you get from range always point to the start of a batch, and each window is n_steps wide.

     1 def get_batches(arr, n_seqs, n_steps):
     2     '''Create a generator that returns batches of size
     3        n_seqs x n_steps from arr.
     4        
     5        Arguments
     6        ---------
     7        arr: Array you want to make batches from
     8        n_seqs: Batch size, the number of sequences per batch
     9        n_steps: Number of sequence steps per batch
    10     '''
    11     # Get the number of characters per batch and number of batches we can make
    12     characters_per_batch = n_seqs * n_steps
    13     n_batches = len(arr) // characters_per_batch
    14     
    15     # Keep only enough characters to make full batches
    16     arr = arr[:n_batches*characters_per_batch]
    17     
    18     # Reshape into n_seqs rows
    19     arr = arr.reshape((n_seqs, -1))
    20     
    21     for n in range(0, arr.shape[1], n_steps):
    22         # The features
    23         x = arr[:, n:n+n_steps]
    24         # The targets, shifted by one
    25         y = np.zeros_like(x)
    26         y[:, :-1], y[:, -1] = x[:, 1:], x[:, 0]
    27         yield x, y
    28 
    29 batches = get_batches(encoded, 10, 50)
    30 x, y = next(batches)
    31 
    32 print('x
    ', x[:10, :10])
    33 print('
    y
    ', y[:10, :10])
  • 相关阅读:
    AngularJs学习——常用表单指令练习
    JavaScript知识递归实现数组中指定后代元素的查找
    JavaScript知识之判断字符串中出现最多的字符及次数
    CSS3知识之立方体动画效果
    CSS知识之 background-size 用法详细介绍
    CSS知识之 background-position 用法详细介绍
    CSS3知识之filter滤镜效果
    CSS3知识之折角效果
    CSS3知识之阴影box-shadow
    JS利用 Sea.js 实现模块化:拖拽、缩放及范围限制
  • 原文地址:https://www.cnblogs.com/knownx/p/8082445.html
Copyright © 2011-2022 走看看