- 博客(13)
- 收藏
- 关注
RSS订阅原创 [CS231n@Stanford] Assignment2-Q2 (python) Batch Normalization 实现 和Q3(python)Dropout 实现
layers.pydef batchnorm_forward(x, gamma, beta, bn_param): """ Forward pass for batch normalization. During training the sample mean and (uncorrected) sample variance are computed from min
2016-09-27 13:07:12
3838
原创 Ubuntu 14.04+cuda 7.0+cudnn 7.0+caffe安装配置+faster-rcnn安装
电脑配置：ubuntu 14.04 64bit128G 内存GTX Titan X显卡软件版本：Cuda 7.0Cudnn-7.01. 安装开发所需的依赖包sudo apt-get install build-essential # basic requirement sudo apt-get install libprotobuf-d
2016-09-26 16:08:52
1419
原创 [CS231n@Stanford] Assignment2-Q1 (python) Fully-connected Neural Network实现
layer.pyimport numpy as npdef affine_forward(x, w, b): """ Computes the forward pass for an affine (fully-connected) layer. The input x has shape (N, d_1, ..., d_k) and contains a minibatc
2016-09-20 14:22:13
4858
原创 [CS231n@Stanford] Assignment1-Q5 (python) features实现
features.ipynbfrom linear_classifier import LinearSVMlearning_rates = [1e-9, 1e-8, 1e-7]regularization_strengths = [1e5, 1e6, 1e7]results = {}best_val = -1best_svm = Nonepass############
2016-09-07 21:05:01
1939
原创 [CS231n@Stanford] Assignment1-Q4 (python) Two layer neural network实现
neural_net.pyimport numpy as npimport matplotlib.pyplot as pltclass TwoLayerNet(object): """ A two-layer fully-connected neural network. The net has an input dimension of N, a hidden lay
2016-09-07 18:48:43
3084
原创 [CS231n@Stanford] Assignment1-Q3 (python) Softmax实现
softmax.pyimport numpy as npfrom random import shuffledef softmax_loss_naive(W, X, y, reg): """ Softmax loss function, naive implementation (with loops) Inputs have dimension D, there are
2016-09-07 13:09:59
2636
原创 [CS231n@Stanford] Assignment1-Q2 (python) SVM实现
linear_svm.pyimport numpy as npfrom random import shuffledef svm_loss_naive(W, X, y, reg): """ Structured SVM loss function, naive implementation (with loops). Inputs have dimension D, the
2016-09-07 10:36:49
2678
1
原创 [CS231n@Stanford] Assignment1-Q1 (python) KNN实现
最近在学习斯坦福的深度学习课程CS231n: Convolutional Neural Networks for Visual Recognition. 课程视频及笔记链接： https://zhuanlan.zhihu.com/p/21930884作业网址：http://cs231n.github.io/assignment1/k_nearest_neighbor.pyi
2016-09-05 11:24:08
2076
原创 【LeetCode从零单排（Java）】No3. Longest Substring Without Repeating Characters
题目： Given a string, find the length of the longest substring without repeating characters. For example, the longest substring without repeating letters for "abcabcbb" is "abc", which the length is 3. For "bbbbb" the longest substring is "b", with the lengt
2016-04-08 15:53:46
439
原创 pybrain 的安装及报错 ImportError:No module named structure的解决方案
最近想用python来做机器学习，发现python下有个开源的神经网络工具包--pybrain可供我们使用。pybrain的安装：我是ubuntu的系统，所以使用命令行安装。sudo pip3 install git+https://github.com/pybrain/pybrain.git安装后使用报错但是再三检查没有问题，安装也正确，随后r
2016-04-03 13:33:51
5808
原创 【LeetCode从零单排（Java）】No2. Add Two Numbers
题目：You are given two linked lists representing two non-negative numbers. The digits are stored in reverse order and each of their nodes contain a single digit. Add the two numbers and return it as
2016-04-03 12:42:58
318
原创 【LeetCode从零单排（Java）】No1.Two Sum
题目Given an array of integers, return indices of the two numbers such that they add up to a specific target.You may assume that each input would have exactly one solution.Example:
2016-03-31 20:19:13
307
转载 Android Studio 1.3及以上 NDK环境配置
自从Android Studio1.3以后，在Android 环境开发JNI程序搭建开发环境变得相对简单。这里就来介绍一下急于Android Studio如何进行jni开发。
2016-03-03 21:10:21
840
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人