【DL】深度学习术语汇编（Deep Learning Terminology）

最新推荐文章于 2022-08-11 22:59:38 发布

北境の守卫

最新推荐文章于 2022-08-11 22:59:38 发布

阅读量531

点赞数

分类专栏： DL 文章标签： Deep Learning Terminology

本文链接：https://blog.csdn.net/baishuo8/article/details/81941289

版权

DL 专栏收录该内容

28 篇文章 0 订阅

订阅专栏

Backto DL Index

文章目录

epoch : 所有训练集使用一次，叫一个 epoch

one epoch = one forward pass and one backward pass of all the training examples

对应代码中的参数是 n_epochs.

batch_size : 一个 batch 中 samples 的个数

一般情况下，一个训练集中会有大量的samples，受限于内存大小通常无法一次加载，同时为了提高训练速度，会将整个training set分为n_batch组，每组包含batch_size个samples

train_set = batch_size * n_batch

batch size = the number of training examples in one forward/backward pass. The higher the batch size, the more memory space you’ll need.

谈谈深度学习中的 Batch_Size

iterations : 利用某个 batch 中的所有samples 进行一次训练，叫一次 iteration

number of iterations = number of passes, each pass using [batch size] number of examples. To be clear, one pass = one forward pass + one backward pass (we do not count the forward pass and backward pass as two different passes)
n_iterations = n_epoch * n_batch

具体流程是

# epoch个数
n_epochs = 100
# 样本总个数
numSamples = 100 000
# 要将样本分割为n_batch组
n_batch = 10
# 每个batch包含的samples
batch_size = numSamples / n_batch 
# 进行训练
iterations = 0
for i in range(n_epochs ):
    for j in range (n_batch):
       #利用第j组batch进行training
       train (j) 
       # iterations个数加1
       iterations = iterations  +1