This media is not supported in your browser
VIEW IN TELEGRAM
MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird’s Eye View Maps
Media is too big
VIEW IN TELEGRAM
YOLOv4 — The most accurate real-time neural network on MS COCO Dataset
This media is not supported in your browser
VIEW IN TELEGRAM
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
This media is not supported in your browser
VIEW IN TELEGRAM
Slime Volleyball Gym Environment
A simple gym environment for testing single and multi-agent reinforcement learning algorithms. Includes a few self-play training examples in python.
A simple gym environment for testing single and multi-agent reinforcement learning algorithms. Includes a few self-play training examples in python.
This media is not supported in your browser
VIEW IN TELEGRAM
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
John Lambert, Zhuang Liu, Ozan Sener, James Hays, and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2020
John Lambert, Zhuang Liu, Ozan Sener, James Hays, and Vladlen Koltun
Computer Vision and Pattern Recognition (CVPR), 2020
This media is not supported in your browser
VIEW IN TELEGRAM
"AI4Animation
This project explores the opportunities of deep learning for character animation and control as part of my Ph.D. research at the University of Edinburgh in the School of Informatics, supervised by Taku Komura..."
This project explores the opportunities of deep learning for character animation and control as part of my Ph.D. research at the University of Edinburgh in the School of Informatics, supervised by Taku Komura..."
Forwarded from Neural Shit
This media is not supported in your browser
VIEW IN TELEGRAM
Классный FaceSwap, позволяет переносить отдельные части лица.
Для желающих поиграться, ноутбук тут
Для желающих поиграться, ноутбук тут
This media is not supported in your browser
VIEW IN TELEGRAM
"...Say goodbye to flatland. We show how curriculum+RL can learn policies to traverse difficult step sequences and variable terrain (rewards only; no example data)..."
YOLO5 is here! https://blog.roboflow.ai/yolov5-is-here/
Roboflow Blog
YOLOv5 is Here: State-of-the-Art Object Detection at 140 FPS
Less than 50 days after the release YOLOv4, YOLOv5 improves accessibility for realtime object detection.
June 29, YOLOv5 has released the first official version of the repository. We wrote a new deep dive on YOLOv5.
June 12, 8:08 AM CDT Update: In response…
June 29, YOLOv5 has released the first official version of the repository. We wrote a new deep dive on YOLOv5.
June 12, 8:08 AM CDT Update: In response…
This media is not supported in your browser
VIEW IN TELEGRAM
DisentangledFaceGAN
This media is not supported in your browser
VIEW IN TELEGRAM
ApartmentPlan 0.2 StyleGAN2
This media is not supported in your browser
VIEW IN TELEGRAM
ApartmentPlan 0.3 StyleGAN2
This media is not supported in your browser
VIEW IN TELEGRAM
"Q. Can we find winning lottery tickets, or sparse trainable deep networks at initialization without ever looking at data?
A. Yes, by conserving "Synaptic Flow" via our new SynFlow algorithm..."
A. Yes, by conserving "Synaptic Flow" via our new SynFlow algorithm..."
This media is not supported in your browser
VIEW IN TELEGRAM
Dance Revolution: Long Sequence Dance Generation
with Music via Curriculum Learning
with Music via Curriculum Learning