How to make simple Telegram bot with TelegramBotAPI

24.08.2017
By
How to make simple Telegram bot with TelegramBotAPI

Very good article (Russian) by Aftamat4ik.ru about installation of Simple Telegram bot with TelegramBotAPI example. How to make cloudflare SSH free certification is here: https://www.lifeofgeek.com/setup-free-ssl-cloudflare/ I have already installed https and skiped this part of article. Also I have used Putty SSH client and asked for SSH login and password for access to hosting. In my case...

Read more »

How to make Facebook Messenger Chatbot

20.08.2017
By
How to make Facebook Messenger Chatbot

You need to install Program0-O free chatbot and follow this instruction https://www.lifeofgeek.com/build-responsive-facebook-messenger-bot/ Some important items of installation: 1. do not forget that limit of symbols in one bot message reply is 640 – need to crop message ore prepare solution what to to with other symbols over 640. 2. images, video, audio files is used...

Read more »

Jupyter notebook installation tricks for Win7 x64

21.07.2017
By

https://github.com/jupyterhub/jupyterhub/issues/444 and sitecustomize.py(Lib\site-packages) with this text inside: import sys; reload(sys); sys.setdefaultencoding(‘ISO-8859-1′) and all will be ok.

Read more »

Traffic signs recognition. Part5. How to recognize traffic sign from video.

06.07.2017
By
Traffic signs recognition. Part5. How to recognize traffic sign from video.

After all steps we need to combine trained RNN to real application which will recognize traffic signs from video stream. Lets’s do it. Python program: #!/usr/bin/env python ''' traffic signs detection with trained RNN traffic_ru_v1.pb USAGE:     ts_detect_2.py ''' # Python 2/3 compatibility from __future__ import print_function from __future__ import division # for...

Read more »

Traffic signs recognition. More simple RNN. Part4.

02.07.2017
By
Traffic signs recognition. More simple RNN. Part4.

There is more simple architecture of RNN with tensorflow but result on russian traffic dataset is bad (about 70% of recognized images with 100000 epoch – training time – about 15 hours). Anyway I will show python program for information.  """ modification of traffic_ru dataset with image preprocession (make YUV mormalized images) from http://jokla.me/robotics/traffic-signs/...

Read more »

Traffic signs recognition. Training RNN and checking result. Part3.

01.07.2017
By
Traffic signs recognition. Training RNN and checking result. Part3.

We have prepared all necessary files after implementation of part 1 and part 2 works. Lets start procedure of learning with tensorflow. TF model part taken at this link (Jiovanny Claudio). Jiovanny gave very good explanation of Tensorflow model which have used for deep learning. I have made some corrections in model for correct...

Read more »