• Application for machine learning by Microsoft
  • (Geektime)

• Convolutional neural network (CNN – Wiki)
• Deep Learning Book review
• Deep Learning Book overview
• DEEP LEARNING Yoshua Bengio

Image Recognition (10 Videos):

• Python: !0 Videos at youtube

Deep / Machine learning resources:

• Comparison of deep learning software
• Comparing Top Deep Learning Frameworks: Deeplearning4j, Torch, Theano, TensorFlow, Caffe, Paddle, MxNet, Keras & CNTK
• TensorFlow – An open-source software library for Machine Intelligence
• Caffe – Deep learning Framework
  • Demo
• Google cloud vision API
• Clarifai
  • Build amazing apps with the world’s best
    image and video recognition API.
• IBM Watson API
  • Learn Watson API
• Amazon Rekognition
• Microsoft project Oxford
  • Extract rich information from images to categorize and process visual data – and machine-assisted moderation of images to help curate your services.

External Links:

• Compared the 3 best image analysis API’s

Clarifai Reference:

• Online Here
• PDF Here

Forum and Help:

• Custom Training

Step by step how to install python, clarify and run a demo code

1. Download & Install Python – Just download and install 2.X
2. Windows
   • Add to system path:
     • c:\python27\
     • c:\python27\scripts\
3. Run example code of Python
   • print “Hello World”
4. Open command prompt and run the following:

   • pip install clarifai==2.0.28

5. Install guide for clarifai
6. After a successful install without error messages, do the following:
   1. change directory to c:\python27\scripts
   2. At command prompt run the following: python clarifai config
7. Provide clarifai_app_id and clarifai app_secret as follows:
   • Under your clarifai account use or create new app. Find HIDE LEGACY AUTHORIZATION
   • The app ID and Secret will be there.
8. Login to your clarifai account
9. Select PREDICT from the following page:
   • https://developer.clarifai.com/quick-start/
10. Copy and paste the following to a python file:

from clarifai.rest import ClarifaiApp

app = ClarifaiApp("{client_id}", "{client_secret}")

# get the general model
model = app.models.get("general-v1.3")

# predict with the model
model.predict_by_url(url='https://samples.clarifai.com/metro-north.jpg')

• Begginers
  • Beginners Tensorflow
  • http://adventuresinmachinelearning.com/python-tensorflow-tutorial/
• YouTube channel of Siraj Raval
• TFLearn: Deep learning library featuring a higher-level API for TensorFlow
• Machine Learning with Python – Tensorflow demo from Video #43 
• Video 52 – Installin CUDA
• Many interesting playlists relating machine learning and many other of sentdex
• Tensorflow API
• Videos – TensorFlow Object Detection API
• Anaconda – Multiple environment for Python
  • Create environment and install tensorflow-gpu.
  • Install Cuda + cuDNN.
  • Check Tensorflow with the following  SCRIPT.

• Presentation:
  • DIY Deep Learning for Vision:
    a Hands-On Tutorial with Caffe
• Build Caffe in Windows with Visual Studio 2013 + CUDA 6.5 + OpenCV 2.4.9
• Github
  • Github Caffe + windows setup and prebuilt
  • Caffe on both Linux and Windows
• How to install Caffe in windows in 5 min
  • Step 1: download Caffe on both Linux and Windows (caffe-master.zip)
  • Step 2: download NVIDIA cuDNN
  • Step 3: Extract  caffe-master.zip
  • Step 4:
    • copy caffe-master/windows/CommonSettings.props.example
    • to copy caffe-master/windows/CommonSettings.props
  • Step 5: Locate  at CommonSettings.props file and update there the GPU capabilities according to the following link:
    • https://developer.nvidia.com/cuda-gpus
  • Step 6: Locate  at CommonSettings.props and write there the path to Cuda.

Machine Learning in Python

• Fatkun Batch Download Image
  • Download batch of images from google search, for model training purposes.

• VGG Convolutional Neural Networks Practical

• Caffe2

• Joseph Redmond – How computers learn to recognize objects instantly

• What is COCO?

  

  COCO is a new image recognition, segmentation, and captioning dataset. COCO has several features:

  • Object segmentation
  • Recognition in Context
  • Multiple objects per image
  • More than 300,000 images
  • More than 2 Million instances
  • 80 object categories
  • 5 captions per image
  • Keypoints on 100,000 people
• Darknet: Open Source Neural Networks in C
  • Tiny Darknet
• YOLO: Real-Time Object Detection
  • Article

Steps to install:

• Install Ubuntu 16.04 lts
• Open terminal and install GIT:
  
  • sudo apt-get update
  • sudo apt-get install git
• Clone Darknet repo
  • git clone https://github.com/pjreddie/darknet.git
  • cd darknet
  • make
  • ./darknet
  • You suppose too get hte following output: usage: ./darknet
• Install OpenCV
  • sudo apt-get install libopencv-dev python-opencv
  • Edit make file and change to OPENCV=1
  • Make again
  • Test by the following command line:
    • ./darknet imtest data/eagle.jpg

How to test Darknet?

• At terminal, at darknet directory write:
  • ./darknet
    • Result: usage: ./darknet

• How to test OpenCV?
  • Open terminal and paste:
    • ./darknet imtest data/eagle.jpg
    • A window with eagle picture will appear.
• How to test darknet predict and classify?
  • Download Extractions.weights. 
  • Open terminal and paste:
    • ./darknet classifier predict cfg/imagenet1k.data cfg/extraction.cfg extraction.weights data/eagle.jpg
      • Result: classification of image.
• How to test Yolo?
  • Download Yolo.weights
  • Open terminal and paste:
    • ./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg
      • Result: image with classification

Darknet Website

• Link: https://pjreddie.com/darknet/yolo/
• Live video:
  • ./darknet detector demo cfg/coco.data cfg/yolo.cfg yolo.weights
• Video from file:
  • ./darknet detector demo cfg/coco.data cfg/yolo.cfg yolo.weights 
• Changing The Detection Threshold
  • ./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg -thresh 0

Docker

• Pull darknet
  • sudo docker pull loretoparisi/darknet
• Test Docker darknet:
  • run darknet
    • docker run –rm -it –name darknet loretoparisi/darknet bash
    • cd darknet
    • ./darknet detector test cfg/coco.data cfg/yolo.cfg /root/yolo.weights data/dog.jpg

• AI
• Machine learning
• Tensorflow
• Deep learning
• Generate models for tensorflow
• Microsoft application for machine learning