原创 【秋招復習——深度學習】ResNet、DenseNet
隨着cnn的發展,尤其是VGG網絡提出以後,大家發現網絡層數是網絡的一個關鍵因素,似乎越深的網絡效 果越好。 但是隨着網絡層數的增加,也出現了梯度消失或者發散。從而導致訓練難以收斂。 隨着normalized initi
原创 ARtoolkit源碼閱讀(一) artoolkit框架simpletest.c
ARToolKit 框架 ARToolKit 是基於opengl和DSVL的增強現實軟件包。它遵循opengl的運行模式,基於幀循環實現3D渲染。 主要流程: 1. 初始化視頻捕獲arVideoCapStart()、讀取文件的
原创 525. Contiguous Array
Total Accepted: 4967 Total Submissions: 14341 Difficulty: Medium Contributors: bishwa Given a binary array, find the
原创 336. Palindrome Pairs
Given a list of unique words, find all pairs of distinct indices (i, j) in the given list, so that the concatenation of
原创 535. Encode and Decode TinyURL
Note: This is a companion problem to the System Design problem: Design TinyURL. TinyURL is a URL shortening service w
原创 350. Intersection of Two Arrays II
Given two arrays, write a function to compute their intersection. Example: Given nums1 = [1, 2, 2, 1], nums2 = [2, 2],
原创 438. Find All Anagrams in a String
Given a string s and a non-empty string p, find all the start indices of p's anagrams in s. Strings consists of lower
原创 290. Word Pattern
Given a pattern and a string str, find if str follows the same pattern. Here follow means a full match, such that there
原创 463. Island Perimeter
You are given a map in form of a two-dimensional integer grid where 1 represents land and 0 represents water. Grid cel
原创 349. Intersection of Two Arrays
Given two arrays, write a function to compute their intersection. Example: Given nums1 = [1, 2, 2, 1], nums2 = [2, 2
原创 299. Bulls and Cows
You are playing the following Bulls and Cows game with your friend: You write down a number and ask your friend to gue
原创 389. Find the Difference
Given two strings s and t which consist of only lowercase letters. String t is generated by random shuffling string s
原创 274. H-Index
Given an array of citations (each citation is a non-negative integer) of a researcher, write a function to compute the
原创 【秋招復習——深度學習】MobileNet
原先模型小型化工作的焦點,放在模型尺度上。 卷積核分解,使用1×N 和N×1的卷積核代替N×N的卷積核 使用bottleneck 結構,以SqueezeNet爲代表 以低精度浮點數保存 冗餘卷積核剪枝以及哈夫曼編碼 depthwi
原创 RCNN學習筆記(1)-RCNN-Rich feature hierarchies for accurate object detection and semantic segmentation論文
reference link1:http://blog.csdn.net/wopawn/article/details/52133338 reference link2: http://blog.csdn.net/shenxiao