Let's do R-CNN with Sklearn-theano

Introduction

I tried using BING with OpenCV as pre-processing for CNN [I tried using Selective search as R-CNN] (http://qiita.com/Almond/items/7850cf81903fbe2a2c6c)

So far, I have done R-CNN using BING and Selective Search. However, if you do CNN (convolutional neural network), would you like to find an object-like part at that time? Rest assured, you can do it! So, this time we will estimate the position with CNN. (* Sklearn-theano's GitHub describes Localizing --position estimation, so I will use this expression below.)

What is Sklearn-theano?

Sklearn-theano is a library that facilitates deep learning by abstracting Theano, a framework for deep learning. A similar one is Keras. This is popular and looks pretty good, but this time it's unnamed? I will try using Sklearn-theano.

Sklearn-theano can do this

As mentioned above, Sklearn-theano can easily classify and estimate images as well as position estimation. In addition, you can easily try the libraries of famous places such as OverFeat, AlexNet, VGGNet, GoogLeNet. I want to solve practical problems using various trained models. Why don't you try using Sklearn-theano?

Let's use it immediately

https://github.com/sklearn-theano/sklearn-theano Clone the above repository and install it with the command python setup.py install. Also, this package is required, so if you haven't installed it, install it first. ・ Numpy ・ Scipy ・ Theano ・ Scikit-learn ・ Pillow

result

This time I tried using plot_single_localization.py in Sample. The position of the sloth is estimated in the last frame. To explain it fairly roughly, we first estimate the points that are likely to be objects in the yellow square area, and then detect the point group that gathered as the final object. Please refer to this page for the detailed detection process.

figure_sloth_example.png

By the way, the processing time is about 310sec .... about 5 minutes! !! !! !! long. .. .. The official statement says 352.80 seconds, so there seems to be no mistake.

Summary

This time, I used a minor library called Sklearn-theano to estimate the position with CNN. If you don't mind taking some time, you may want to try it. However, I think it is tough, needless to say, when speed is required. ** If anyone knows a general object detection method that can withstand real time, please let us know **

Recommended Posts

Let's do R-CNN with Sklearn-theano
Let's do image scraping with Python
Let's do MySQL data manipulation with Python
Let's do web scraping with Python (weather forecast)
Let's do web scraping with Python (stock price)
Let's do Raspberry Pi?
Do Houdini with Python3! !! !!
Let's play with 4D 4th
Do Django with CodeStar (Python3.6.8, Django2.2.9)
Let's play with Amedas data-Part 1
Do Django with CodeStar (Python3.8, Django2.1.15)
Let's make Othello with wxPython
Let's play with Amedas data-Part 4
Let's make dice with tkinter
Let's write python with cinema4d.
Do AES encryption with DJango
Let's play with Amedas data-Part 3
Let's play with Amedas data-Part 2
Let's build git-cat with Python
Do something fuzzing with acceptableRegex.py
Do multi-stage SSH with Fabric
Let's execute commands regularly with cron!
Do not switch with pyenv global!
Let's do "Hello World" in 40 languages! !!
What to do with Magics install
Let's make a GUI with python.
HTTPS with Django and Let's Encrypt
Let's learn Deep SEA with Selene
Let's make a breakout with wxPython
Let's play with Excel with Python [Beginner]
To do tail recursion with Python2
What to do with PYTHON release?
I want to do ○○ with Pandas
Let's make a graph with python! !!
Let's make a supercomputer with xCAT
Let's make Othello AI with Chainer-Part 2-
Let's recognize emotions with Azure Face
Let's analyze voice with Python # 1 FFT
Python | What you can do with Python