Realtime Coherent Style Transfer for Videos https://t.co/HDpMbikCGe #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) May 30, 2019
Realtime Coherent Style Transfer for Videos https://t.co/HDpMbikCGe #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) May 30, 2019
EfficientNet is an open source library that uses a new compound model scaling method and leverages recent progress in #AutoML to improve #neuralnetwork scaling techniques, achieving state-of-the-art accuracy with up to 10x better efficiency. Learn more ↓ https://t.co/g1fPbxRFev
— Google AI (@GoogleAI) May 29, 2019
An self-contained image segmentation example (model trained from scratch on the Oxford Pets dataset): https://t.co/GLbowTf9ie
— François Chollet (@fchollet) May 29, 2019
Kmnist Benchmark japanese handwriting recognition competition: $1000 in compute credits to the contributor of the highest validation accuracy by July 8. Kuzushiji-MNIST is a drop-in replacement for the MNIST dataset (28x28 grayscale, 70,000 images) https://t.co/UuPvVKdMnF
— Peter Skomoroch (@peteskomoroch) May 28, 2019
Evaluating generative models is hard! We propose Classification Accuracy Score from classifiers trained on generated data:
— Oriol Vinyals (@OriolVinyalsML) May 28, 2019
-Accuracy of 43% when trained purely on BigGAN samples (vs 73%)
-Naive data augmentation doesn't work (yet!)
Paper: https://t.co/dN6xfVlyqE
cc @SumanRavuri pic.twitter.com/7HsdZFGzek
Build a Hardware-Based Face Recognition System for $150 With the Nvidia Jetson Nano and Python https://t.co/RbIf4soI5h
— PyCoder’s Weekly (@pycoders) May 26, 2019
Interesting new "Simple Self Attention layer" that improves all tested resnet baselines on Imagenette and Imagewoof. Seems like something worth looking into further!https://t.co/W8JLqvVUya pic.twitter.com/PIIy0nXHfm
— Jeremy Howard (@jeremyphoward) May 25, 2019
The Convolutional Tsetlin Machine peaks at 99.51% accuracy on MNIST with a single layer of interpretable filters in… https://t.co/pHncQjVK47
— /MachineLearning (@slashML) May 24, 2019
A moving demonstration that deep learning is all about adding depth where it wasn't before.. https://t.co/wBfKzy3MpM
— Jeff Dean (@JeffDean) May 24, 2019
torchvision 0.3.0: segmentation, detection models, new datasets, C++/CUDA operators
— PyTorch (@PyTorch) May 23, 2019
Blog with link to tutorial, release notes: https://t.co/7PuNpMrL58
Install commands have changed, use the selector on https://t.co/DeaBDSRxs8 pic.twitter.com/Ljt7rSymno
Finished retraining my WikiArt model with StyleGAN. Now I can do style transfer directly on the latents! Lots of directions this could go. pic.twitter.com/PcBXzXp6iQ
— Gene Kogan (@genekogan) May 14, 2019
DeepRED: Deep Image Prior Powered by RED
— ML Review (@ml_review) May 5, 2019
w/ @docmilanfar
Unsupervised restoration algorithm combines Deep Image Prior with the Regularization by Denoising (RED) while avoiding the need to differentiate the chosen denoiserhttps://t.co/yrl2ppJmwv pic.twitter.com/a9cpn0ONNJ