PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset. https://t.co/skw18iP6A7 #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) October 21, 2018
PyTorch implementation of DeepLabV3, trained on the Cityscapes dataset. https://t.co/skw18iP6A7 #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #pytorch
— PyTorch Best Practices (@PyTorchPractice) October 21, 2018
Anyone here familiar with the 'What do Deep Networks Like to See' paper? One of our students has noticed it seems to be making some odd conclusions based on checkerboard artifacts, but I haven't studied the paper closely enough to tell if this is an errorhttps://t.co/s4guQQ67nQ
— Jeremy Howard (@jeremyphoward) October 13, 2018
{mmdetection, mmcv} by Multimedia Lab @ CUHK
— PyTorch (@PyTorch) October 12, 2018
- a modular, object detection and segmentation framework
- fast state-of-the-art models like Mask RCNN, RetinaNet, etc.
- powered the winning entry of COCO Detection 2018 challenge.https://t.co/taHOGeDdwWhttps://t.co/QQdlOYwCsB
“Recycle-GAN”: Unsupervised Video Retargeting. Translation from John Oliver to Stephen Colbert, and a synthesized flower follows the blooming process with the input flower. Website has more video demos demonstrating video retargeting for faces and flowers: https://t.co/yv0WANiY5d pic.twitter.com/XDA5bWzK1S
— hardmaru (@hardmaru) October 12, 2018
Noise2Noise: Learning Image Restoration without Clean Data - Official TensorFlow implementation of the ICML 2018 paper https://t.co/Lj5Ka9WsxB #deeplearning #machinelearning #ml #ai #neuralnetworks #datascience #tensorflow
— TensorFlow Best Practices (@TFBestPractices) October 11, 2018
Imitation from watching videos (in this case, from YouTube) by virtual characters -- directly imitating acrobatic skills, dance, etc. via deep RL + HMR for pose recovery: https://t.co/Eum9jLZ7DJ https://t.co/m2JtLgF5wz
— Sergey Levine (@svlevine) October 9, 2018
AKA "friends don't let friends use VGG" https://t.co/VuzRrZJYhh
— Jeremy Howard (@jeremyphoward) October 8, 2018
Object-Contrastive Networks: Unsupervised Object Representations. ICLR 2019 submission with relevance to the #computervision community. https://t.co/DksoYGZjXE pic.twitter.com/fG4MJS1IOT
— Tomasz Malisiewicz (@quantombone) October 3, 2018
We have fun with WGAN in https://t.co/aQsW5afov6, and I challenge students to try to get something working that's even better. Some nice results here from a student using SAGAN+D2GAN+SNGAN, showing a "woman->man" latent space :)https://t.co/2BjWF4HH01 pic.twitter.com/JdBgj9zFh5
— Jeremy Howard (@jeremyphoward) September 30, 2018
Code and paper available: https://t.co/ffWGvcJAxt
— Jeremy Howard (@jeremyphoward) September 28, 2018
I think @VinceMarron's "Style Transfer as Optimal Transfer" method, developed as a @fastdotai student project, remains the best style transfer method I've ever seen pic.twitter.com/Qxg08Tc51W
— Jeremy Howard (@jeremyphoward) September 28, 2018
Google Brain team researchers @ekindogus, @barret_zoph, and @quocleix have open sourced the AutoAugment image classification policies that achieve state-of-the-art results. Check out the the paper and code is located in tensorflow/models/research/autoaugment. #AutoML https://t.co/p4ZNxbzh5t
— Google AI (@GoogleAI) September 27, 2018