Увеличение видео 1080P до 4К, или Как я научился не волноваться и полюбил апскейл с помощью нейросетей
https://habr.com/ru/post/446032/
https://habr.com/ru/post/446032/
Хабр
Увеличение видео 1080P до 4K, или Как я научился не волноваться и полюбил апскейл с помощью нейросетей
Читая недавно очередную статью про апскейл ( Upscale — масштабирование изображения до более высокого разрешения), на этот раз про коммерческий продукт Topaz AI Gigapixel, я оставил комментарий...
Evaluating the Unsupervised Learning of Disentangled Representations
http://ai.googleblog.com/2019/04/evaluating-unsupervised-learning-of.html
http://ai.googleblog.com/2019/04/evaluating-unsupervised-learning-of.html
Googleblog
Evaluating the Unsupervised Learning of Disentangled Representations
Hyperparameter optimization in python. Part 1: Scikit-Optimize.
https://towardsdatascience.com/hyperparameter-optimization-in-python-part-1-scikit-optimize-754e485d24fe
https://towardsdatascience.com/hyperparameter-optimization-in-python-part-1-scikit-optimize-754e485d24fe
MuseNet deep neural network that can generate 4-minute musical compositions with 10 different instruments
https://openai.com/blog/musenet/
https://openai.com/blog/musenet/
Openai
MuseNet
We’ve created MuseNet, a deep neural network that can generate 4-minute musical compositions with 10 different instruments, and can combine styles from country to Mozart to the Beatles. MuseNet was not explicitly programmed with our understanding of music…
How to Implement VGG, Inception and ResNet Modules for Convolutional Neural Networks from Scratch
https://machinelearningmastery.com/how-to-implement-major-architecture-innovations-for-convolutional-neural-networks/
https://machinelearningmastery.com/how-to-implement-major-architecture-innovations-for-convolutional-neural-networks/
How to Start Competing on Kaggle
https://towardsdatascience.com/how-to-begin-competing-on-kaggle-bd9b5f32dbbc
https://towardsdatascience.com/how-to-begin-competing-on-kaggle-bd9b5f32dbbc
A pytorch-toolbelt is a Python library with a set of bells and whistles for PyTorch for fast R&D prototyping and Kaggle farming
https://github.com/BloodAxe/pytorch-toolbelt
https://github.com/BloodAxe/pytorch-toolbelt
GitHub
GitHub - BloodAxe/pytorch-toolbelt: PyTorch extensions for fast R&D prototyping and Kaggle farming
PyTorch extensions for fast R&D prototyping and Kaggle farming - BloodAxe/pytorch-toolbelt
A Gentle Introduction to 1×1 Convolutions to Reduce the Complexity of Convolutional Neural Networks
https://machinelearningmastery.com/introduction-to-1x1-convolutions-to-reduce-the-complexity-of-convolutional-neural-networks/
https://machinelearningmastery.com/introduction-to-1x1-convolutions-to-reduce-the-complexity-of-convolutional-neural-networks/
MachineLearningMastery.com
A Gentle Introduction to 1×1 Convolutions to Manage Model Complexity - MachineLearningMastery.com
Pooling can be used to down sample the content of feature maps, reducing their width and height whilst maintaining their salient features. A problem with deep convolutional neural networks is that the number of feature maps often increases with the depth…
Forwarded from Artificial Intelligence
Announcing the 6th Fine-Grained Visual Categorization Workshop
http://ai.googleblog.com/2019/04/announcing-6th-fine-grained-visual.html
http://ai.googleblog.com/2019/04/announcing-6th-fine-grained-visual.html
Googleblog
Announcing the 6th Fine-Grained Visual Categorization Workshop
Создаем с нуля собственную нейронную сеть на Python
https://habr.com/ru/company/mailru/blog/449416/
https://habr.com/ru/company/mailru/blog/449416/
Deep Learning Lecture
https://www.youtube.com/watch?v=FQw2l0AJ2iw
https://www.youtube.com/watch?v=FQw2l0AJ2iw
YouTube
(Old) Lecture 26 | (3/4) Deep Reinforcement Learning - TD and SARSA
Carnegie Mellon University
Course: 11-785, Intro to Deep Learning
Offering: Spring 2019
For more information, please visit: http://deeplearning.cs.cmu.edu/
Contents:
• Reinforcement Learning
• TD Learning
• SARSA
Course: 11-785, Intro to Deep Learning
Offering: Spring 2019
For more information, please visit: http://deeplearning.cs.cmu.edu/
Contents:
• Reinforcement Learning
• TD Learning
• SARSA
Five Machine Learning Paradoxes that will Change the Way You Think About Data
https://towardsdatascience.com/five-machine-learning-paradoxes-that-will-change-the-way-you-think-about-data-e100be5620d7
https://towardsdatascience.com/five-machine-learning-paradoxes-that-will-change-the-way-you-think-about-data-e100be5620d7
Medium
Five Machine Learning Paradoxes that will Change the Way You Think About Data
Paradoxes are one of the marvels of human cognition that are hard to using math and statistics. Conceptually, a paradox is a statement…
Automating Optimization of Quantized Deep Learning Models on CUDA
https://tvm.ai/2019/04/29/opt-cuda-quantized.html
https://tvm.ai/2019/04/29/opt-cuda-quantized.html
A Gentle Introduction to the ImageNet Large Scale Visual Recognition Challenge (ILSVRC)
https://machinelearningmastery.com/introduction-to-the-imagenet-large-scale-visual-recognition-challenge-ilsvrc/
https://machinelearningmastery.com/introduction-to-the-imagenet-large-scale-visual-recognition-challenge-ilsvrc/
MachineLearningMastery.com
A Gentle Introduction to the ImageNet Challenge (ILSVRC) - MachineLearningMastery.com
The rise in popularity and use of deep learning neural network techniques can be traced back to the innovations in the application of convolutional neural networks to image classification tasks.
Some of the most important innovations have sprung from submissions…
Some of the most important innovations have sprung from submissions…
Пошаговое руководство по созданию голосового помощника с Python
https://habr.com/ru/post/450224/
https://habr.com/ru/post/450224/
Real-Time Patch-Based Stylization of Portraits
Using Generative Adversarial Network
http://dcgi.fel.cvut.cz/home/sykorad/facestyleGAN.html
Using Generative Adversarial Network
http://dcgi.fel.cvut.cz/home/sykorad/facestyleGAN.html
dcgi.fel.cvut.cz
Real-Time Patch-Based Stylization of Portraits Using Generative Adversarial Network
Ensemble methods: bagging, boosting and stacking
https://towardsdatascience.com/ensemble-methods-bagging-boosting-and-stacking-c9214a10a205
https://towardsdatascience.com/ensemble-methods-bagging-boosting-and-stacking-c9214a10a205
Towards Data Science
Ensemble learning: Bagging and Boosting | Towards Data Science
It's time to explore the world of bagging and boosting. With these powerful techniques, you can improve the performance of your models...
BoTorch is a library for Bayesian Optimization built on PyTorch.
Facebook open-sources Ax and BoTorch to simplify AI model optimization
github: https://github.com/pytorch/botorch
denoscription: https://techcrunch.com/2019/05/01/facebook-open-sources-ax-and-botorch-to-simplify-ai-model-optimization/
Facebook open-sources Ax and BoTorch to simplify AI model optimization
github: https://github.com/pytorch/botorch
denoscription: https://techcrunch.com/2019/05/01/facebook-open-sources-ax-and-botorch-to-simplify-ai-model-optimization/
GitHub
GitHub - pytorch/botorch: Bayesian optimization in PyTorch
Bayesian optimization in PyTorch. Contribute to pytorch/botorch development by creating an account on GitHub.
Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & Retrieval
http://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html
http://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html
research.google
Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & R
Posted by Bingyi Cao and Tobias Weyand, Software Engineers, Google AI Last year we released Google-Landmarks, the largest world-wide landmark rec...
Best Practices for Preparing and Augmenting Image Data for Convolutional Neural Networks
https://machinelearningmastery.com/best-practices-for-preparing-and-augmenting-image-data-for-convolutional-neural-networks/
https://machinelearningmastery.com/best-practices-for-preparing-and-augmenting-image-data-for-convolutional-neural-networks/
MachineLearningMastery.com
Best Practices for Preparing and Augmenting Image Data for CNNs - MachineLearningMastery.com
It is challenging to know how to best prepare image data when training a convolutional neural network. This involves both scaling the pixel values and use of image data augmentation techniques during both the training and evaluation of the model. Instead…