I put together everything needed to get started on the @kaggle Humpback Whale Identification challenge using @fastdotai and @pytorch v1: https://t.co/dyuvLmemEf
— Radek Osmulski (@radekosmulski) December 14, 2018
Features resnet50 trained using curriculum learning in a way tailored to the dataset. Local CV tracks LB score closely pic.twitter.com/y8DDKN8mjq
DGL (Deep Graph Library) - Clean and efficient library to build graph neural networks including GCN, TreeLSTM and graph generative models. Includes auto-batching and other tricks for speed.https://t.co/A5n4G292Rb pic.twitter.com/RbQqhAFJLu
— PyTorch (@PyTorch) December 12, 2018
fastai has now been updated for the release version of @pytorch v1. You can install cuda, cudnn, pytorch, torchvision, and fastai with a single line.
— Jeremy Howard (@jeremyphoward) December 8, 2018
In fact, here's a pic showing all the steps necessary to install, download data, and create and fine-tune a pretrained model :) pic.twitter.com/oBuAKD0Cvo
[v1.0] : JIT Compiler, Faster Distributed, C++ Frontend, CUDA10
— PyTorch (@PyTorch) December 7, 2018
Read more about the changes at https://t.co/Xfrad06NZO
As always, get the install commands on https://t.co/DeaBDSRxs8
Advances in few-shot learning: reproducing results in PyTorch by Oscar Knagg https://t.co/U4g0oTwn6J #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) December 1, 2018
Making Your Neural Network Say “I Don’t Know” — Bayesian NNs using Pyro and PyTorch by @paraschopra https://t.co/uIJXniArqw #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) November 30, 2018
Visualizing the Loss Landscape of Neural Nets #NIPS2018
— ML Review (@ml_review) November 27, 2018
By @ljk628
Explores how network architecture affects the loss landscape and its effect of generalization
PyTorchhttps://t.co/qb7F1AorsO
ArXivhttps://t.co/5BTWX9ifNS pic.twitter.com/Dscrlb44rS
Ignite - a lightweight library to help with training neural networks in PyTorch https://t.co/DuFuLGpleg #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) November 25, 2018
Face Alignment in Full Pose Range: A 3D Total Solutionhttps://t.co/FQCGKa6UX2
— PyTorch (@PyTorch) November 23, 2018
- the inference time is about 0.27ms per image (input batch with 128 images) on GeForce GTX TITAN X. pic.twitter.com/6Qwf717xcZ
EuclidesDB by @tarantulae: a ML feature database, supporting / serving multiple PyTorch models at a time, fine-tuning, kNN, written in C++, gRPC interface (HTTP2 + Protobuf), leveldb integration.https://t.co/GkAU10klPN pic.twitter.com/WiW6Icu1PT
— PyTorch (@PyTorch) November 22, 2018
A lot of PyTorch-powered entries at the top of the DAWNBench deep learning benchmark, which measures training speed, inference latency and cost.https://t.co/tP9HORizcX https://t.co/tP9HORizcX
— Yann LeCun (@ylecun) November 12, 2018
The FAIR folks have a brand new course on #DeepLearning and #PyTorch on @udacity. https://t.co/DaxYWNy393 pic.twitter.com/tc5Gz1UafV
— Delip Rao (@deliprao) November 9, 2018
