bonelee - 博客园

2018年3月11日

leetcode 521. Longest Uncommon Subsequence I

摘要： Given a group of two strings, you need to find the longest uncommon subsequence of this group of two strings. The longest uncommon subsequence is defi 阅读全文

posted @ 2018-03-11 20:32 bonelee 阅读(203) 评论(0) 推荐(0)

python 循环高级用法 [expression for x in X [if condition] for y in Y [if condition] ... for n in N [if condition] ]按照从左至右的顺序，分别是外层循环到内层循环

摘要：高级语法除了像上面介绍的 [x ** 2 for x in L] 这种基本语法之外，列表推导式还有一些高级的扩展。 4.1. 带有if语句我们可以在 for 语句后面跟上一个 if 判断语句，用于过滤掉那些不满足条件的结果项。例如，我想去除列表中所有的偶数项，保留奇数项，可以这么写： >>> 阅读全文

posted @ 2018-03-11 18:33 bonelee 阅读(36065) 评论(5) 推荐(13)

leetcode 637. Average of Levels in Binary Tree

摘要： Given a non-empty binary tree, return the average value of the nodes on each level in the form of an array. Example 1: Note: 解法1: 精简版：解法2: DFS 使用一个数组阅读全文

posted @ 2018-03-11 17:49 bonelee 阅读(434) 评论(0) 推荐(0)

2018年3月10日

leetcode 496. Next Greater Element I

摘要： You are given two arrays (without duplicates) nums1 and nums2 where nums1’s elements are subset of nums2. Find all the next greater numbers for nums1' 阅读全文

posted @ 2018-03-10 22:01 bonelee 阅读(286) 评论(0) 推荐(0)

leetcode 463. Island Perimeter

摘要： You are given a map in form of a two-dimensional integer grid where 1 represents land and 0 represents water. Grid cells are connected horizontally/ve 阅读全文

posted @ 2018-03-10 08:39 bonelee 阅读(376) 评论(0) 推荐(0)

2018年3月9日

leetcode 682. Baseball Game

摘要： You're now a baseball game point recorder. Given a list of strings, each string can be one of the 4 following types: Each round's operation is permane 阅读全文

posted @ 2018-03-09 23:14 bonelee 阅读(221) 评论(0) 推荐(0)

leetcode 566. Reshape the Matrix

摘要： In MATLAB, there is a very useful function called 'reshape', which can reshape a matrix into a new one with different size but keep its original data. 阅读全文

posted @ 2018-03-09 21:43 bonelee 阅读(192) 评论(0) 推荐(0)

Python：SMOTE算法——样本不均衡时候生成新样本的算法

摘要： Python：SMOTE算法直接用python的库， imbalanced-learn imbalanced-learn is a python package offering a number of re-sampling techniques commonly used in dataset 阅读全文

posted @ 2018-03-09 17:26 bonelee 阅读(38364) 评论(0) 推荐(1)

CNN 文本分类模型优化经验——关键点：加卷积层和FC可以提高精度，在FC前加BN可以加快收敛，有时候可以提高精度，FC后加dropout，conv_1d的input维度加大可以提高精度，但是到256会出现OOM。

摘要：迭代一次，acc是98.5%多一点。如果使用： acc是95%多一点点。使用类似 vgg的模型， https://github.com/AhmetHamzaEmra/tflearn/blob/master/examples/images/VGG19.py acc是98.5%多一点,稍微比第一种模阅读全文

posted @ 2018-03-09 16:20 bonelee 阅读(3251) 评论(1) 推荐(0)

padding valid same区别——就是是否补齐0的问题

摘要：参考：https://stackoverflow.com/questions/37674306/what-is-the-difference-between-same-and-valid-padding-in-tf-nn-max-pool-of-t If you like ascii art: "V 阅读全文

posted @ 2018-03-09 11:00 bonelee 阅读(5857) 评论(0) 推荐(0)

将者，智、信、仁、勇、严也。

Hi，我是李智华，华为-安全AI算法专家，欢迎来到安全攻防对抗的有趣世界。

公告