In the words of Russian MYC although is engaged in computer vision, but in school never contact neural network, let alone deep learning. When he was looking for a job, Deep learning was just beginning to get into people's eyes.
But now if you are lucky enough to be interviewed by Myc, he will ask you this question Deep Learning why call Deep Learning. What's the difference between a regular machine learning?
If you can't answer it, it doesn't matter, because as an engineer, we just know how to use it in MATLAB (not
In order to show how far-reaching the impact of deep learning on computer vision, MYC prepared the following small demo for us.
How to get the program to identify something in the diagram.
Anyway, Matlab is doing this first you have to have neural network Toolbox if you have computer Vision System Toolbox is better, here we use him to provide
Helperimportmatconvnet
To help us import a neural network.
3. You have to have a GPU that supports CUDA.
First of all, we do not want to download the trained network of Daniel, Alexnet is a network of 1000 different objects provided by imagenet, in other words, he knows these 1000 kinds of things, beyond this scope does not know
Cnnurl = ' Http://www.vlfeat.org/matconvnet/models/beta16/imagenet-caffe-alex.mat ';
% Store CNN model in a temporary folder
Cnnmatfile = FullFile (tempdir, ' Imagenet-caffe-alex.mat ');
If ~exist (cnnmatfile, ' file ')% download only once
disp (' downloading pre-trained CNN model ... ');
WeBSave (Cnnmatfile, cnnurl);
End
Next, import into Matlab
Convnet = Helperimportmatconvnet (cnnmatfile)
Read our pictures
I = Imread (' sherlock.jpg ');
Alexnet model needs a picture is a 227x227x3 color map
I = Imresize (i,[227,227]);
Activate the last category layer
Category = Activations (convnet,i, ' classificationlayer ');
Find the class with the highest probability
[~,idx] = max (category);
See what it is?
Convnet. Layers (end). Classnames{idx}
ans =
' n02099712 '
Go back to imagenet and see which category it is.
It was Labrador, magical. The most important thing is that there is no brain in the whole process. Boss: Yes Myc, so soon to recognize the dog out of the
Myc: where, borrowed the results of others
Boss: Actually, this dog is Golden retriever
Myc: ...
Boss: No, in fact, people are often mistaken, redouble their efforts.
Myc: ... That's my fault.
Author: Potter
Link: https://zhuanlan.zhihu.com/p/20944764
Source: Know