NLP for Computer Vision – Having breakfast with Terminator

In this video, we are talking about another tool of Machine Learning- Natural Language Processor- which could be used to enhance the accuracy and power of computer vision. Natural Language Processing or NLP is used to understand the meaning of human language by training an algorithm that looks for the relationship between words. One of these relationships could be “belongs to” or “contains”, and so we can relate several concrete terms (fruit, cereals, milk) with an abstract concept that contains all (breakfast, morning). We can use this feature to increase our accuracy in detecting concepts in a scene. We also propose this method for the use case “Contextual Advertising” to avoid wrong detections derived from the context of a video:

0:00 – Intro
0:37 – Object Detection
1:07 – NLP definition
1:16 – Context example 1: BREAKFAST
2:00 – Context expample 2: BASEBALL
2:23 – Contextual advertising USE CASE
3:00 – Recap

  • Comments are Closed

Tech Talk Introduction to Machine Learning. Neuronal networks – Computer Vision – NLP

Tech Talk Introduction to Machine Learning (Neuronal networks – Computer Vision – NLP) & Tensorflow Tutorial:

00:00 – Tech Talk topics

01:15 – Introduction to Machine Learning

03:43 – Types of Learning (Supervised & Unsupervised)

05:36 – Linear Regression and Gradient Descend

12:33 – Bias & Variance

16:35 – Non linear functions (Logistic Regression and Sigmoid)

18:37 – Neuronal Networks

24:00 – Activation Functions (Identity, Sigmoid and ReLU)

25:31 – Computer Vision

29:37 – Convolution

34:01 Convolutional Neural Networks (CNN)

35:20 – NLP (Natural Lenguage Programming)

37:03 – Tensorflow Tutorial

45:40 – Tensorflow Demo

 

keep learning with Epic Academy

 

DASH Industry Forum, New dash.js v2.6.5 released

DASH Industry Forum, New dash.js v2.6.5 released

DASH Industry Forum, New dash.js v2.6.5 released

Epic Labs, proud member of the DASH Industry Forum and Digital Production Partnership, announces that version 2.6.5 of the dash.js player has been released.
Two main functionalities have been added in this version of the player: Image type adaptations and thumbnails support for UI scrubbing, and improved management of multi period streams.
To implement the thumbnails, the DASH Industry Forum defined an stream track for images in addition to the existing ones for video and audio: http://dashif.org/wp-content/uploads/2017/09/DASH-IF-IOP-v4.1-clean.pdf. With this new track, a user can get the typical frames inside the seeking bar, appearing an image related to the video content just at that moment.
The other important novelty is the improved support of multiperiod streams. With this functionality, a dash.js stream can be composed of different sub-streams, each of which refers to a specific period. This allows to play different videos through the player at any time and without the need for extra logic.
This has a vital importance, for example, in the dynamic insertion of ads because it allows advertising to be played as if it were another part of the content, making a clean cut without any kind of waiting or buffering, mixing content in a continuous way as if it were a single stream, from a single manifest.

 

The DASH Industry Forum (DASH-IF) establishes interoperability gui- delines on the usage of the MPEG-DASH streaming standard. MPEG- DASH simpli es and converges the delivery of IP video, to provide a rich and enjoyable user experience, to help drive down costs and ultimately to enable a better content catalogue to be offered to consumers.

 

Epic Labs, proud member of the DASH Industry Forum, is a software engineering center that helps companies to innovate in Media, offering advanced video solutions and several collaboration proposals in digital transformation.

 

 

Stable GPU TensorFlow 1.3 environment. By Ignacio Peletier

Using GPUs for training machine learning applications can speed operations up to 40 times faster than using a common CPU. In this video a stable environment for using TensorFlow 1.3 with CUDA is presented and a simple script is given so we can assure we are using our GPU!

Cuda 8.0 → http://docs.nvidia.com/cuda/cuda-installation-guide-linux/#axzz4VZnqTJ2A
cuDNN 6.0 → https://developer.nvidia.com/cudnn (requires sign up)
Tensorflow 1.3 → https://www.tensorflow.org/

Pip and virtualenv:

sudo apt-get install python-pip python-dev build-essential
sudo pip install --upgrade pip
sudo pip install --upgrade virtualenv

Create virtual enviroment´s directory:

mkdir my_envs && cd my_envs

Create virtualenv:

virtualenv env

Activate virtualenv:

source env/bin/activate

Installing tensorflow-gpu:

pip install tensorflow-gpu #pip≥8.1

Running the script:

python tutorial.py

keep learning with Epic Academy

  • Comments are Closed

Inteligencia Artificial real para Broadcast y Media BIT Experience

Video y Power Point del workshop ofrecido por Epic Labs y Antonio Tablero (FOX) sobre Inteligencia Artificial, Machine Learning, para Media y Broadcast el pasado 4 de octubre en BIT Experience 2017. (http://www.ifema.es/bitexperience_01).
Incluimos en esta sección el vídeo completo, un resumen de 10´con los puntos clave y el Power Point que se utilizó con toda la información.

VIDEO RESUMEN

VIDEO COMPLETO

DESCARGAR PRESENTACIÓN

  • Comments are Closed