junsong-wang / deep-learning Goto Github PK
View Code? Open in Web Editor NEWdeep learning courses
deep learning courses
使用修改后的classify.py,测试mnist模型。测试图片为单通道的28*28
error:
Traceback (most recent call last):
File "python/classifymnist.py", line 178, in
main(sys.argv)
File "python/classifymnist.py", line 134, in main
channel_swap=channel_swap)
File "/home/ouy/Downloads/caffe/python/caffe/classifier.py", line 40, in init
self.transformer.set_channel_swap(in_, channel_swap)
File "/home/ouy/Downloads/caffe/python/caffe/io.py", line 217, in set_channel_swap
raise Exception('Channel swap needs to have the same number of '
Exception: Channel swap needs to have the same number of dimensions as the input channels.
阅读文献 “Imagenet classification with deep convolutional neural networks”
挑一个Caffe里的一个例子,详细理解Solver文件里每一个超参数的意义。
请根据下面给出的专有名词,自我评价掌握的程度,
(0: 没听说过, 1: 只听说过概念, 2:系统学习过,但基本忘了,3:系统学习过,还基本记得,4:概念原理比较清楚,5:在实际系统中用过)
向量的基本概念,内积,模,范数等
矩阵的基本概念, 乘法,逆,秩等
矩阵的分解, EVD和SVD分解,特征值和特征向量, 子空间的概念
概率论,条件概率,前验概率和后验概率,贝叶斯公式,线性回归
随机过程,马尔可夫链,隐形马克可夫链
一维相关和卷积的概念,FFT,二维卷积
凸函数和凸优化的基本方法
FIR滤波器,卡尔曼滤波器,粒子滤波
机器学习的基本概念, 有监督学习和无监督学习, 过拟合,正则化
经典机器学习算法, 决策树,随机森林,逻辑斯蒂回归,贝叶斯分类器,SVM分类器等
人工神经网络的基本概念,BP算法。
卷积神经网络的基本概念,2D卷积,池化。
基本的CNN网络,Alexnet,GoogleNet, VGG, ResNet, MobileNet等
基本的目标检测算法, Faster-RCNN, SSD, YOLO等
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.