Implementation of Deep Learning model for image recognition

1.First of all

This article shows how to implement a Deep Learning program on your computer. Since the purpose is image recognition, we will implement a practical scale convolutional neural network (CNN).

2. Preparing the machine

A Linux machine is recommended as a high performance GPU is essential. The main choices for Linux machines are:

  1. Desktop PC
  2. Virtual environment (Virtual Box, etc.)
  3. AWS(Amazon Web Service)

Put CentOS or Ubuntu in any of the above and use it.

3. GPU settings

To use the GPU, you need to install CUDA and cuDNN. For Ubuntu 14.04, refer to http://qiita.com/shinya_ohtani/items/f374ed0dd51737087369.

4. Python installation

Install a distribution called Anaconda on your Linux machine, which contains Python itself and various modules. The procedure is almost OK as described in http://morimori2008.web.fc2.com/contents/PCprograming/python/pythonAnaconda.html. However, we will install it as a local user here.

5. Library for Deep Learning

Next, make the library for building Deep Learning models available in Python. I chose Theano here. From the terminal

$ pip install theano

To install Theano.

6. Code implementation

From the terminal

$ jupyter notebook

By typing, the Python development environment will be launched. We will implement the code on this. For implementation, http://deeplearning.net/tutorial will be helpful. The CNN source code is also available on this site and can be used for image recognition as it is.

7. Future outlook

At this point, you have implemented CNN.

After that, collect the input data to be actually used and prepare the input / output format for that data to complete the image recognition program.

Recommended Posts

Implementation of Deep Learning model for image recognition
Deep learning image recognition 2 model implementation
Image recognition model using deep learning in 2016
Deep learning image recognition 3 after model creation
Read & implement Deep Residual Learning for Image Recognition
Deep learning image recognition 1 theory
Deep reinforcement learning 2 Implementation of reinforcement learning
[AI] Deep Learning for Image Denoising
Othello-From the tic-tac-toe of "Implementation Deep Learning" (3)
Othello-From the tic-tac-toe of "Implementation Deep Learning" (2)
Deep learning 1 Practice of deep learning
Basic principles of image recognition technology (for beginners)
Deep learning learned by implementation (segmentation) ~ Implementation of SegNet ~
Model construction for face image dataset sorting-VGG19 transfer learning (# 2)
Count the number of parameters in the deep learning model
Techniques for understanding the basis of deep learning decisions
Othello ~ From the tic-tac-toe of "Implementation Deep Learning" (4) [End]
Deep running 2 Tuning of deep learning
Deep learning for compound formation?
Application of CNN2 image recognition
Implementation of Scale-space for SIFT
[For beginners of deep learning] Implementation of simple binary classification by full coupling using Keras
[Deep Learning from scratch] Implementation of Momentum method and AdaGrad method
Japanese translation of public teaching materials for Deep learning nanodegree
Real-time image recognition on mobile devices with TensorFlow learning model
Classify CIFAR-10 image datasets using various models of deep learning
Deep Learning Model Lightening Library Distiller
Deep learning learned by implementation 1 (regression)
Image recognition of fruits using VGG16
I searched for a similar card of Hearthstone with Deep Learning
Summary of pages useful for studying the deep learning framework Chainer
Introduction to Deep Learning for the first time (Chainer) Japanese character recognition Chapter 3 [Character recognition using a model]
Python: Basics of image recognition using CNN
Meaning of deep learning models and parameters
Qiskit: Implementation of Quantum Circuit Learning (QCL)
Make your own PC for deep learning
Try deep learning of genomics with Kipoi
Machine learning algorithm (implementation of multi-class classification)
Visualize the effects of deep learning / regularization
Sentiment analysis of tweets with deep learning
I tried using the trained model VGG16 of the deep learning library Keras
Image alignment: from SIFT to deep learning
[Reinforcement learning] Easy high-speed implementation of Ape-X!
[Deep learning] Nogizaka face detection ~ For beginners ~
Image recognition
Let's make Godzilla's image recognition model preprocessing, learning and deployment feel good
Deep Learning
Learning record of reading "Deep Learning from scratch"
About data expansion processing for deep learning
Introduction to Deep Learning for the first time (Chainer) Japanese character recognition Chapter 2 [Model generation by machine learning]
Python vs Ruby "Deep Learning from scratch" Chapter 4 Implementation of loss function
Python implementation of continuous hidden Markov model
Python vs Ruby "Deep Learning from scratch" Chapter 3 Implementation of 3-layer neural network
Machine Learning: Image Recognition of MNIST by using PCA and Gaussian Native Bayes
Deep Learning from scratch The theory and implementation of deep learning learned with Python Chapter 3
Build a python environment to learn the theory and implementation of deep learning
Python: Deep learning in natural language processing: Implementation of answer sentence selection system
Implementation of a model that predicts the exchange rate (dollar-yen rate) by machine learning
The story of doing deep learning with TPU
I tried image recognition of CIFAR-10 with Keras-Learning-
The story of low learning costs for Python