#آموزش

Getting started with Deep Learning using Keras and TensorFlow in R

🔗 https://www.analyticsvidhya.com/blog/2017/06/getting-started-with-deep-learning-using-keras-in-r/

✔️Installation of Keras with tensorflow at the backend.
✔️Different types models that can be built in R using Keras
✔️Classifying MNIST handwritten digits using an MLP in R
✔️Comparing MNIST result with equivalent code in Python

#deep_learning #keras #TensorFlow #R

#آموزش

How I Built a Reverse Image Search with Machine Learning and TensorFlow
[Published Jun 07, 2017]

🔗Part 1:
https://www.codementor.io/jimmfleming/how-i-built-a-reverse-image-search-with-machine-learning-and-tensorflow-part-1-8dje8gjm9

🔗Part 2:
https://www.codementor.io/jimmfleming/how-i-built-a-reverse-image-search-with-machine-learning-and-tensorflow-part-2-8lri6k4x5

#Image_Search #TensorFlow #machine_learning

#آموزش

Deep Learning With TensorFlow, Nvidia and Apache Mesos (DC/OS) (Part 1)
[Published Jun 06, 2017]


✏️Tutorial #1: Run a #TensorFlow #Docker image on your laptop and run a #Machine_Learning model with and without GPUs.
✏️Tutorial #2: Run a Tensoflow Docker image on a DC/OS #cluster with and without GPUs. See #GPU isolation and #Jupyter in action.
✏️Tutorial #3: Deploy a dynamic, #distributed TensorFlow on DC/OS from the Universe. See how TensorFlow on DC/OS dynamically consumes and releases resources on the cluster when done. Run multiple TensorFlows on the same cluster with different resource requirements.

🔗 https://dzone.com/articles/deep-learning-with-tensorflow-nvidia-and-apache-me

#deep_learning #TensorFlow #Nvidia #Apache_Mesos

استفاده از پهباد برای رساندن توپ به داور در فینال جام حذفی پرتغال!

#مقاله 2013
Network In Network
https://arxiv.org/pdf/1312.4400.pdf
#Mlpconv_layer #deep_learning #CNN #convolutional_neutral_network

Deep Learning: Transfer Learning in 10 lines of MATLAB Code

https://blogs.mathworks.com/pick/2017/02/24/deep-learning-transfer-learning-in-10-lines-of-matlab-code/

#deep_learning #matlab

📝 مروری بر مسابقه‌ بزرگ هوش مصنوعی پیش‌بینی انتخابات ریاست جمهوری

⏱چهارشنبه 24 خردادماه (ساعت 16-18)
👤مهندس مجید زرین‌کلاه
🏛کلاس101دانشکده کامپیوتر

ثبتنام: goo.gl/qJdvns

@BigDataWorkGroup

#آموزش
Short history of the #Inception deep learning architecture

🔗 http://nicolovaligi.com/history-inception-deep-learning-architecture.html

Inception in #TensorFlow
🔗 https://github.com/tensorflow/models/tree/master/inception

#inception #cnn #convolutional_neutral_network #deep_learning

Network In Network, Lin et al. (2014)
https://arxiv.org/pdf/1312.4400v3.pdf

Going deeper with convolutions, Szegedy et al. (2014)
https://arxiv.org/pdf/1409.4842v1.pdf

Rethinking the inception architecture for computer vision, Szegedy et al. (2015)
https://arxiv.org/pdf/1512.00567v3.pdf

v4: Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning, Szegedy et al. (2016)
https://arxiv.org/pdf/1602.07261v2.pdf

Conclusion and pretrained models

#مقاله #سورس #کد

IMDB-WIKI – 500k+ face images with age and gender labels
pic: http://bit.ly/2rZNDJx

دیتاست سن و جنسیت افراد؛ جمع آوری شده از صفحات ویکی پدیا
+
مقاله و مدل در Caffe , و وزنهای آموزش دیده شده شبکه



https://data.vision.ee.ethz.ch/cvl/rrothe/imdb-wiki/

#Gender_prediction #age #Deep_Learning #dataset #model
#CNN #convolutional_neutral_network

#مقاله #سورس_کد

Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks
pic: http://bit.ly/2srFGOS
(Submitted on 11 Apr 2016)
#MTCNN

در الگوریتمهای قدیمی تشخیص چهره, موقعیت سر, حالات چهره، نور و ... تاثیر گذار بود و الگوریتم های موجود را با مشکل مواجه میکرد.
الگوریتمهایی نظیر Viola and Jones - Haar-cascade که در opencv پیاده سازی شده برای چهر های رو به رو و نزدیک رو به رو خوب کار میکند اما برای چهره هادر موقعیت ای دیگر کارایی ندارد!
تیم تحقیقاتی ماکروسافت با ارائه مقاله ای در سال 2014 با عنوان
Joint Cascade Face Detection and Alignment
با جنگل تصادفی این مشکل را تا حد زیادی برطرف کرد و سرعت هم تا حدود 30 میلی ثانیه برای تصاویر VGA بهبود داد، اما انتخاب ویژگی های دستی پرفورمنس را محدود کرده بود.

اما در این مقاله با کمک یادگیری عمیق دقت تا حد خوبی افزایش یافته و همانن مقاله ماکروسافت علاوه بر تشخیص کار face alignment هم انجام میشود.
در این روش 3 شبکه عصبی کانولوشنالی پشت سر هم و به صورت آبشاری قرار گرفته است
شبکه اول: بسیار سبک برای پیدا کردن تمامی نواحی مشکوک به وجود چهره.
شبکه دوم : این شبکه از از خروجی شبکه اول ورودی میگیرد؛ نواحی اشتباه پیدا شده را حذف میکند.
شبکه سوم: کاری شبیه یه شبکه دوم بر روی نواحی باقی مانده, همچنین پیدا کردن landmark های چهره نظیر چشم ها و بینی و alignment نقاط.



🕐Runtime efficiency:
It takes 16fps on a 2.60GHz CPU and 99fps on GPU (Nvidia Titan Black)

🔗abstract:
https://arxiv.org/abs/1604.02878

🔗Paper:
https://arxiv.org/pdf/1604.02878

🔗Project Page:
https://kpzhang93.github.io/MTCNN_face_detection_alignment/

🔗codes:
⚙️#Matlab / #Caffe implementation :
http://bit.ly/2rvkr9Q
⚙️#Python / #Tensorflow implementation :
http://bit.ly/2t1fB6e

#face #face_detection #face_alignment #MTCNN
#deep_learning #cnn #convolutional_neutral_network

#خبر

For the first time ever, #NumPy—a core project for the #Python scientific computing stack—has received #grant funding. The proposal, “Improving NumPy for Better Data Science” will receive $645,020 from the Moore Foundation over 2 years, with the funding going to UC Berkeley Institute for Data Science.

https://www.numfocus.org/blog/numpy-receives-first-ever-funding-thanks-to-moore-foundation/

🙏Thanks to: @cyberbully_gng

Face detection

تصویر مقاله
https://t.me/cvision/249

Deep Learning without Backpropagation
[Tutorial: DeepMind's Synthetic Gradients]

https://iamtrask.github.io/2017/03/21/synthetic-gradients/?utm_content=buffer6d5d4&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer

✔️Part 1: #Synthetic Gradients Overview
✔️Part 2: Using Synthetic Gradients
✔️Part 3: Generating Synthetic Gradients
✔️Part 4: A Baseline Neural Network
✔️?
✔️Part 6: Synthetic Gradients Based on Layer Output

#مقاله منتشر شده توسط گوگل

#MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
(Submitted on 17 Apr 2017)

We present a class of efficient models called MobileNets for #mobile and embedded #vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between #latency and #accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

🔗 https://arxiv.org/pdf/1704.04861.pdf

#deep_learning #cnn #convolutional_neutral_network

#خبر
#Google open-sources mobile-first computer vision models for TensorFlow
pic: http://bit.ly/2sbzqYu
[Published June 14, 2017]

گوگل mobileNet منتشر شده در مقاله دو ماه پیش را به صورت متن باز برای #تنسورفلو منتشر کرد.

شبکه های از پیش آموزش داده شده مناسب برای بازشناسی اشیاء در موبایل.

🔗 https://research.googleblog.com/2017/06/mobilenets-open-source-models-for.html
🔗 https://venturebeat.com/2017/06/14/google-open-sources-mobile-first-computer-vision-models-for-tensorflow/


✒️مرتبط با:
✔️تنسورفلو برای اندروید:
https://t.me/cvision/208
✔️مقاله mobileNet
https://t.me/cvision/254

#TensorFlow #TensorFlow #TensorFlow_Lite #convolutional_neutral_network
#pre_train #computer_vision

#MobileNet #preTrain
https://t.me/cvision/255

#آموزش در سایت ماکروسافت
Learning Image to Image Translation with CycleGANs
[Published June 12, 2017]
https://www.microsoft.com/reallifecode/2017/06/12/learning-image-image-translation-cyclegans/

مرتبط با https://t.me/cvision/214

#CycleGAN #GAN #Generative #CNN #Convolutional #deep_learning #adversarial #Generative_Models #Generative

#MobileNet Accuracy
https://t.me/cvision/255

#MobileNet: Pre_Trained Tensorflow Computer Vision Models.

Developers who want to start using these models should go to the Tensorflow Mobile page:
🔗 https://www.tensorflow.org/mobile/
More information about theTensorflow-Slim image classification library is available on Github:
🔗 https://github.com/tensorflow/models/blob/master/slim/README.md

#TensorFlow #pre_train #model #vision

#Tensorflow #benchmark, #CPU VS #GPU
http://www.nvidia.com/object/gpu-accelerated-applications-tensorflow-benchmarks.html