Benchmarks for popular CNN models
🔗 https://github.com/jcjohnson/cnn-benchmarks
Some general conclusions:
- Pascal Titan X > GTX 1080
- GTX 1080 > Maxwell Titan X
- ResNet > VGG
- Always use cuDNN
- GPUs are critical
#Benchmark #Deep_Learning #CNN #GPU #Model
🔗 https://github.com/jcjohnson/cnn-benchmarks
Some general conclusions:
- Pascal Titan X > GTX 1080
- GTX 1080 > Maxwell Titan X
- ResNet > VGG
- Always use cuDNN
- GPUs are critical
#Benchmark #Deep_Learning #CNN #GPU #Model
GitHub
GitHub - jcjohnson/cnn-benchmarks: Benchmarks for popular CNN models
Benchmarks for popular CNN models. Contribute to jcjohnson/cnn-benchmarks development by creating an account on GitHub.
#آموزش
LSTM by Example using Tensorflow
https://medium.com/towards-data-science/lstm-by-example-using-tensorflow-feb0c1968537
#deep_learning #LSTM #TensorFlow
LSTM by Example using Tensorflow
https://medium.com/towards-data-science/lstm-by-example-using-tensorflow-feb0c1968537
#deep_learning #LSTM #TensorFlow
Medium
LSTM by Example using Tensorflow
In Deep Learning, Recurrent Neural Networks (RNN) are a family of neural networks that excels in learning from sequential data. A class of…
#مقاله
Perceptual Generative #Adversarial Networks for Small Object Detection
https://arxiv.org/abs/1706.05274
Perceptual Generative #Adversarial Networks for Small Object Detection
https://arxiv.org/abs/1706.05274
Advice:
#TensorFlow is a safe bet for most projects. Not perfect but has huge community, wide usage. Maybe pair with high-level wrapper (#Keras, #Sonnet, etc)
I think #PyTorch is best for #research. However still new, there can be rough patches.
Use TensorFlow for one graph over many machines
✔️Consider #Caffe, #Caffe2, or TensorFlow for production deployment
✔️Consider TensorFlow or Caffe2 for #mobile
🖇source: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture8.pdf
#deep_learning #framework
#TensorFlow is a safe bet for most projects. Not perfect but has huge community, wide usage. Maybe pair with high-level wrapper (#Keras, #Sonnet, etc)
I think #PyTorch is best for #research. However still new, there can be rough patches.
Use TensorFlow for one graph over many machines
✔️Consider #Caffe, #Caffe2, or TensorFlow for production deployment
✔️Consider TensorFlow or Caffe2 for #mobile
🖇source: http://cs231n.stanford.edu/slides/2017/cs231n_2017_lecture8.pdf
#deep_learning #framework
Deep learning frameworks in GitHub:
http://www.cio.com/article/3193689/artificial-intelligence/which-deep-learning-network-is-best-for-you.html
#framework #deep_learning
http://www.cio.com/article/3193689/artificial-intelligence/which-deep-learning-network-is-best-for-you.html
#framework #deep_learning
PyTorch vs TensorFlow — spotting the difference
[Published June 21, 2017]
https://medium.com/@dubovikov.kirill/pytorch-vs-tensorflow-spotting-the-difference-25c75777377b
#PyTorch #TensorFlow #deep_learning #framework
[Published June 21, 2017]
https://medium.com/@dubovikov.kirill/pytorch-vs-tensorflow-spotting-the-difference-25c75777377b
#PyTorch #TensorFlow #deep_learning #framework
Medium
PyTorch vs TensorFlow — spotting the difference
In this post I want to explore some of the key similarities between PyTorch and TensorFlow
#کورس #آموزش
دوره رایگان آموزش مبانی یادگیری عمیق توسط ماکروسافت
این دوره از 5 تیر 96 آغاز شده و طول این دوره 6 هفته است.
در این دوره با فریم ورک CNTK یا Microsoft Cognitive Toolkit آشنا خواهید شد.
Free EDX Course: " Deep Learning Explained "
Starts - Jun 27, 2017
Course Syllabus:
Week 1: Introduction to deep learning and a quick recap of machine learning concepts.
Week 2: Building a simple multi-class #classification model using logistic regression
Week 3: Detecting digits in hand-written digit image, starting by a simple end-to-end model, to a deep neural network
Week 4: Improving the hand-written digit #recognition with #convolutional network
Week 5: Building a model to forecast time data using a #recurrent network
Week 6: Building text data application using recurrent #LSTM (long short term memory) units
🔗 https://www.edx.org/course/deep-learning-explained-microsoft-dat236x
#course #Microsoft #edx #deep_learning #CNTK
دوره رایگان آموزش مبانی یادگیری عمیق توسط ماکروسافت
این دوره از 5 تیر 96 آغاز شده و طول این دوره 6 هفته است.
در این دوره با فریم ورک CNTK یا Microsoft Cognitive Toolkit آشنا خواهید شد.
Free EDX Course: " Deep Learning Explained "
Starts - Jun 27, 2017
Course Syllabus:
Week 1: Introduction to deep learning and a quick recap of machine learning concepts.
Week 2: Building a simple multi-class #classification model using logistic regression
Week 3: Detecting digits in hand-written digit image, starting by a simple end-to-end model, to a deep neural network
Week 4: Improving the hand-written digit #recognition with #convolutional network
Week 5: Building a model to forecast time data using a #recurrent network
Week 6: Building text data application using recurrent #LSTM (long short term memory) units
🔗 https://www.edx.org/course/deep-learning-explained-microsoft-dat236x
#course #Microsoft #edx #deep_learning #CNTK
edX
Deep Learning Explained
Learn an intuitive approach to building the complex models that help machines solve real-world problems with human-like intelligence.
#خبر #آموزش
فیلمهای سمینار زمستانهی شریف 2016 در کانال یوتیوب سمینار آپلود شده است.
فیلم ارائه دکتر علی اسلامی با موضوع
Beyond Supervised Deep Learning
شدیدا توصیه میشود.
Sharif Winter Seminar Series
🎥 https://www.youtube.com/channel/UC5-ct_yxHQJTYJP3TkeEDmQ
⏱ مورخ 8 و 9 دی 1395
مطالب مرتبط:
مباحث مرتبط به یادگیری ژرف در سمینار زمستانه شریف: https://news.1rj.ru/str/cvision/44
صوت ضبط شده ی دکتر اسلامی در 8 دی 96 در سمینار زمستانی شریف: https://news.1rj.ru/str/cvision/92
اسلایدهای ارائه دکتر اسلامی در 8 دی 95 در سمینار زمستانی شریف: https://news.1rj.ru/str/cvision/78
اسلایدهای ارائه دکتر اسلامی در سمینار 11 دی 96 دانشگاه تهران: https://news.1rj.ru/str/cvision/80
فیلم ارائه دکتر علی اسلامی در سمینار 11 دی 95 دانشگاه تهران: https://news.1rj.ru/str/cvision/103
#deep_learning #Ali_Eslami #Vision #seminar
#سمینار
فیلمهای سمینار زمستانهی شریف 2016 در کانال یوتیوب سمینار آپلود شده است.
فیلم ارائه دکتر علی اسلامی با موضوع
Beyond Supervised Deep Learning
شدیدا توصیه میشود.
Sharif Winter Seminar Series
🎥 https://www.youtube.com/channel/UC5-ct_yxHQJTYJP3TkeEDmQ
⏱ مورخ 8 و 9 دی 1395
مطالب مرتبط:
مباحث مرتبط به یادگیری ژرف در سمینار زمستانه شریف: https://news.1rj.ru/str/cvision/44
صوت ضبط شده ی دکتر اسلامی در 8 دی 96 در سمینار زمستانی شریف: https://news.1rj.ru/str/cvision/92
اسلایدهای ارائه دکتر اسلامی در 8 دی 95 در سمینار زمستانی شریف: https://news.1rj.ru/str/cvision/78
اسلایدهای ارائه دکتر اسلامی در سمینار 11 دی 96 دانشگاه تهران: https://news.1rj.ru/str/cvision/80
فیلم ارائه دکتر علی اسلامی در سمینار 11 دی 95 دانشگاه تهران: https://news.1rj.ru/str/cvision/103
#deep_learning #Ali_Eslami #Vision #seminar
#سمینار
YouTube
Winter Seminar Series - WSS
Winter Seminar Series - WSS
Advanced Topics in Computer Science and Engineering
Sharif University of Technology
Students' Scientific Chapter
سری سمینارهای زمستانه
مباحث پیشرفته در علوم و مهندسی کامپیوتر
دانشگاه صنعتی شریف
http://wss-sharif.com
Advanced Topics in Computer Science and Engineering
Sharif University of Technology
Students' Scientific Chapter
سری سمینارهای زمستانه
مباحث پیشرفته در علوم و مهندسی کامپیوتر
دانشگاه صنعتی شریف
http://wss-sharif.com
Media is too big
VIEW IN TELEGRAM
#ارائه_علمی
فیلم ارائه دکتر علی اسلامی در سمینار زمستانه شریف 95
ALI ESLAMI, GOOGLE DEEPMIND
TITLE: Beyond Supervised Deep Learning
فیلم ارائه دکتر علی اسلامی در سمینار زمستانه شریف 95
ALI ESLAMI, GOOGLE DEEPMIND
TITLE: Beyond Supervised Deep Learning
Convex Optimization
Complete Playlist for the Course:
https://www.youtube.com/view_play_list?p=3940DD956CDF0622
EE 364A Course lectures:
http://stanford.edu/class/ee364a/lectures.html
Complete Playlist for the Course:
https://www.youtube.com/view_play_list?p=3940DD956CDF0622
EE 364A Course lectures:
http://stanford.edu/class/ee364a/lectures.html
YouTube
Lecture Collection | Convex Optimization - YouTube
Stanford Electrical Engineering Course on Convex Optimization.
Oxford Deep NLP 2017 course lecture notes and videos
🔗 https://github.com/oxford-cs-deepnlp-2017/lectures
#deep_learning #NLP #course #video #oxford
🔗 https://github.com/oxford-cs-deepnlp-2017/lectures
#deep_learning #NLP #course #video #oxford
GitHub
GitHub - oxford-cs-deepnlp-2017/lectures: Oxford Deep NLP 2017 course
Oxford Deep NLP 2017 course. Contribute to oxford-cs-deepnlp-2017/lectures development by creating an account on GitHub.
Media is too big
VIEW IN TELEGRAM
#ارائه_علمی
📝 Predictive Learning: the Next Frontier in A.I.
👤Yann LeCun, Facebook AI director
🕐 March 2017
🏛 Nokia Bell Labs
More: http://bit.ly/2sQoOhY
#Yann_LeCun #deep_learning
📝 Predictive Learning: the Next Frontier in A.I.
👤Yann LeCun, Facebook AI director
🕐 March 2017
🏛 Nokia Bell Labs
More: http://bit.ly/2sQoOhY
#Yann_LeCun #deep_learning
بر آمدن عید و برون رفتن روزه
ساقی بدهم باده بر باغ و به سبزه
حافظ منشین بی می و معشوق زمانی
کایام گل و یاسمن و عید صیام است
🎊🎉🎊🎉🎊🎉🎊🎉
@CVision
ساقی بدهم باده بر باغ و به سبزه
حافظ منشین بی می و معشوق زمانی
کایام گل و یاسمن و عید صیام است
🎊🎉🎊🎉🎊🎉🎊🎉
@CVision
#خبر
pic: http://bit.ly/2sGcxOS
Andrew Ng announces Deeplearning.ai, his new venture after leaving Baidu
🔗 https://techcrunch.com/2017/06/23/deeplearning/
http://Deeplearning.ai
#Andrew_Ng #deep_learning
pic: http://bit.ly/2sGcxOS
Andrew Ng announces Deeplearning.ai, his new venture after leaving Baidu
🔗 https://techcrunch.com/2017/06/23/deeplearning/
http://Deeplearning.ai
#Andrew_Ng #deep_learning
Media is too big
VIEW IN TELEGRAM
#آموزش
Using TensorFlow on AWS
فیلم آموزشی دانشگاه toronto پیرامون راه اندازی تنسورفلو در سرورهای پردازشی AWS آمازون و اجرای AlexNet روی این سرورها.
مرتبط با:
https://news.1rj.ru/str/cvision/169
#AWS #amazon
Using TensorFlow on AWS
فیلم آموزشی دانشگاه toronto پیرامون راه اندازی تنسورفلو در سرورهای پردازشی AWS آمازون و اجرای AlexNet روی این سرورها.
مرتبط با:
https://news.1rj.ru/str/cvision/169
#AWS #amazon
#کورس #دانشگاهی
دو کورس یادگیری ماشین از دانشگاه toronto :
CSC411: Machine Learning and Data Mining (Winter 2017)
http://www.cs.toronto.edu/~guerzhoy/411/
CSC321: Introduction to Machine Learning and Neural Networks (Winter 2016)
http://www.cs.toronto.edu/~guerzhoy/321/
ویدیوهای مربوط به این دو کورس در کانال یوتیوب مدرس آن موجود است:
https://www.youtube.com/channel/UCLGWA_gS-sGcChq3D2M4jSA/videos
لازم به ذکر است از زبان #پایتون و فریم ورک #TensorFlow در این دو کورس آموزشی استفاده میشود.
#course #machine_learning #ML #video
دو کورس یادگیری ماشین از دانشگاه toronto :
CSC411: Machine Learning and Data Mining (Winter 2017)
http://www.cs.toronto.edu/~guerzhoy/411/
CSC321: Introduction to Machine Learning and Neural Networks (Winter 2016)
http://www.cs.toronto.edu/~guerzhoy/321/
ویدیوهای مربوط به این دو کورس در کانال یوتیوب مدرس آن موجود است:
https://www.youtube.com/channel/UCLGWA_gS-sGcChq3D2M4jSA/videos
لازم به ذکر است از زبان #پایتون و فریم ورک #TensorFlow در این دو کورس آموزشی استفاده میشود.
#course #machine_learning #ML #video
YouTube
Michael Guerzhoy
#آموزش
image caption generator in Keras
https://github.com/oarriaga/neural_image_captioning/blob/master/src/visualization.ipynb
🙏Thanks to: @cyberbully_gng
#keras #deep_learning #captioning
image caption generator in Keras
https://github.com/oarriaga/neural_image_captioning/blob/master/src/visualization.ipynb
🙏Thanks to: @cyberbully_gng
#keras #deep_learning #captioning
GitHub
oarriaga/neural_image_captioning
Neural image captioning (NIC) implementation with Keras 2. - oarriaga/neural_image_captioning
#مقاله
Network Dissection: Quantifying Interpretability of Deep Visual Representations
(Submitted on 19 Apr 2017)
pic: http://bit.ly/2tlfHbv
✔️Our paper investigates three questions:
-What is a disentangled representation, and how can its factors be quantified and detected?
-Do interpretable hidden units reflect a special alignment of feature space, or are interpretations a chimera?
-What conditions in state-of-the-art training lead to representations with greater or lesser entanglement?
🔗abstract:
https://arxiv.org/abs/1704.05796
🔗Paper:
http://netdissect.csail.mit.edu/final-network-dissection.pdf
🔗Project Page (code + data):
http://netdissect.csail.mit.edu/
#deep_learning #CNN
Network Dissection: Quantifying Interpretability of Deep Visual Representations
(Submitted on 19 Apr 2017)
pic: http://bit.ly/2tlfHbv
✔️Our paper investigates three questions:
-What is a disentangled representation, and how can its factors be quantified and detected?
-Do interpretable hidden units reflect a special alignment of feature space, or are interpretations a chimera?
-What conditions in state-of-the-art training lead to representations with greater or lesser entanglement?
🔗abstract:
https://arxiv.org/abs/1704.05796
🔗Paper:
http://netdissect.csail.mit.edu/final-network-dissection.pdf
🔗Project Page (code + data):
http://netdissect.csail.mit.edu/
#deep_learning #CNN
#آموزش
Modeling documents with Generative Adversarial Networks
[Published June 28, 2017]
Generative Adversarial Networks or GANs have become a significant part of deep learning research since they were introduced by Ian Goodfellow et al back in 2014.
Have you wondered if/how GANs can be used to model textual documents? John Glover explores this in his well-written blog post (with code in #TensorFlow).
http://blog.aylien.com/modeling-documents-generative-adversarial-networks/
#deep_learning #GAN
Modeling documents with Generative Adversarial Networks
[Published June 28, 2017]
Generative Adversarial Networks or GANs have become a significant part of deep learning research since they were introduced by Ian Goodfellow et al back in 2014.
Have you wondered if/how GANs can be used to model textual documents? John Glover explores this in his well-written blog post (with code in #TensorFlow).
http://blog.aylien.com/modeling-documents-generative-adversarial-networks/
#deep_learning #GAN
AYLIEN
Modeling documents with Generative Adversarial Networks - AYLIEN
In this post I provide a brief overview of the Generative Adversarial Networks paper and walk through some of the code.