Glenn Jocher
YOU?
Author Swipe
View article: ultralytics/yolov5: v6.0 - YOLOv5n 'Nano' models, Roboflow integration, TensorFlow export, OpenCV DNN support
ultralytics/yolov5: v6.0 - YOLOv5n 'Nano' models, Roboflow integration, TensorFlow export, OpenCV DNN support Open
This release incorporates many new features and bug fixes (465 PRs from 73 contributors) since our last release v5.0 in April, brings architecture tweaks, and also introduces new P5 and P6 'Nano' models: <…
View article: ultralytics/yolov3: v9.5.0 - YOLOv5 v5.0 release compatibility update for YOLOv3
ultralytics/yolov3: v9.5.0 - YOLOv5 v5.0 release compatibility update for YOLOv3 Open
This YOLOv3 release merges the most recent updates to YOLOv5 featured in the April 11th, 2021 YOLOv5 v5.0 release into this repository. This is part of routine Ultralytics maintenance and takes place on every major YOLOv5 …
View article: ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations
ultralytics/yolov5: v5.0 - YOLOv5-P6 1280 models, AWS, Supervise.ly and YouTube integrations Open
This release implements YOLOv5-P6 models and retrained YOLOv5-P5 models: YOLOv5-P5 models (same architecture as v4.0 release): 3 output layers P3, P4, P5 at strides 8, 16, 32, trained at -…
View article: ultralytics/yolov3: v9.1 - YOLOv5 Forward Compatibility Updates
ultralytics/yolov3: v9.1 - YOLOv5 Forward Compatibility Updates Open
This release is a minor update implementing numerous bug fixes, feature additions and performance improvements from https://github.com/ultralytics/yolov5 to this repo. Models remain unchanged from v9.0 release. Branch Notice The ultralytic…
View article: ultralytics/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration
ultralytics/yolov5: v4.0 - nn.SiLU() activations, Weights & Biases logging, PyTorch Hub integration Open
This release implements two architecture changes to YOLOv5, as well as various bug fixes and performance improvements. Breaking Changes nn.SiLU() activations replace nn.LeakyReLU(0.1) and nn.Hardswish() activations used in previous version…
View article: ultralytics/yolov3: v9.0 - YOLOv5 Forward Compatibility Release
ultralytics/yolov3: v9.0 - YOLOv5 Forward Compatibility Release Open
This release is a major update to the https://github.com/ultralytics/yolov3 repository that brings forward-compatibility with YOLOv5, and incorporates numerous bug fixes, feature additions and performance improvements from https://github.c…
View article: ultralytics/yolov3: v8 - Final Darknet Compatible Release
ultralytics/yolov3: v8 - Final Darknet Compatible Release Open
This is the final release of the darknet-compatible version of the https://github.com/ultralytics/yolov3 repository. This release is backwards-compatible with darknet *.cfg files for model configuration. All pytorch (.pt) and darknet (…
View article: ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements
ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements Open
This release aggregates various minor bug fixes and performance improvements since the main v3.0 release and incorporates PyTorch 1.7.0 compatibility updates. v3.1 models share weights with v3.0 models but contain minor module updates (inp…
View article: ultralytics/yolov5: v3.0
ultralytics/yolov5: v3.0 Open
Breaking Changes This release does not contain breaking changes. Bug Fixes Hyperparameter evolution fixed, tutorial added (https://github.com/ultralytics/yolov5/issues/607) Added Functionality PyTorch 1.6 native AMP replaces NVIDIA Apex…
View article: ultralytics/yolov5: v2.0
ultralytics/yolov5: v2.0 Open
Breaking Changes IMPORTANT: v2.0 release contains breaking changes. Models trained with earlier versions will not operate correctly with v2.0. The last commit before v2.0 that operates correctly with all earlier pretrained models is: https…
View article: ultralytics/yolov5: Initial Release
ultralytics/yolov5: Initial Release Open
YOLOv5 1.0 Release Notes June 22, 2020: PANet updates: increased layers, reduced parameters, faster inference and improved mAP 364fcfd. June 19, 2020: FP16 as new default for smaller checkpoints and faster…
View article: ultralytics/yolov3: [email protected]:0.95 on COCO2014
ultralytics/yolov3: [email protected]:0.95 on COCO2014 Open
This release requires PyTorch >= v1.4 to function properly. Please install the latest version from https://github.com/pytorch/pytorch/releases Breaking Changes There are no breaking changes in this release. Bug Fixes Various Added Function…
View article: ultralytics/flickr_scraper: Release v1
ultralytics/flickr_scraper: Release v1 Open
Release v1
View article: ultralytics/COCO2YOLO: Improvements
ultralytics/COCO2YOLO: Improvements Open
Minor corrections and improvements Supports dataset division into train, test and validate groups now
View article: ultralytics/yolov3: Rectangular Inference, Conv2d + Batchnorm2d Layer Fusion
ultralytics/yolov3: Rectangular Inference, Conv2d + Batchnorm2d Layer Fusion Open
This release requires PyTorch >= v1.0.0 to function properly. Please install the latest version from https://github.com/pytorch/pytorch/releases Breaking Changes There are no breaking changes in this release. Bug Fixes NMS now screens out…
View article: ultralytics/xview-yolov3: Initial Release
ultralytics/xview-yolov3: Initial Release Open
xView 2018 Object Detection Challenge: YOLOv3 Training and Inference.
View article: WAVE: Machine Learning for Full-Waveform Time-Of-Flight Detectors
WAVE: Machine Learning for Full-Waveform Time-Of-Flight Detectors Open
We propose a WAveform Vector Exploitation (WAVE) deep neural network for full-waveform Time-Of-Flight (TOF) physics detectors, and evaluate its performance against traditional reconstruction techniques via Monte Carlo study of a small plas…
View article: Studies of MCP-PMTs in the miniTimeCube neutrino detector
Studies of MCP-PMTs in the miniTimeCube neutrino detector Open
This report highlights two different types of cross-talk in the photodetectors of the miniTimeCube neutrino experiment. The miniTimeCube detector has 24 8 × 8-anode Photonis MCP-PMT Planacon XP85012, totalling 1536 individual pixels viewin…
View article: Multiple-photon disambiguation on stripline-anode Micro-Channel Plates
Multiple-photon disambiguation on stripline-anode Micro-Channel Plates Open
View article: Correction: Corrigendum: AGM2015: Antineutrino Global Map 2015
Correction: Corrigendum: AGM2015: Antineutrino Global Map 2015 Open
Every second greater than 10 25 antineutrinos radiate to space from Earth, shining like a faint antineutrino star. Underground antineutrino detectors have revealed the rapidly decaying fission products inside nuclear reactors, verified the…
View article: Letter of Intent: The Atmospheric Neutrino Neutron Interaction Experiment (ANNIE)
Letter of Intent: The Atmospheric Neutrino Neutron Interaction Experiment (ANNIE) Open
View article: Letter of Intent: The Accelerator Neutrino Neutron Interaction Experiment (ANNIE)
Letter of Intent: The Accelerator Neutrino Neutron Interaction Experiment (ANNIE) Open
Neutron tagging in Gadolinium-doped water may play a significant role in reducing backgrounds from atmospheric neutrinos in next generation proton-decay searches using megaton-scale Water Cherenkov detectors. Similar techniques might also …
View article: A new type of Neutrino Detector for Sterile Neutrino Search at Nuclear Reactors and Nuclear Nonproliferation Applications
A new type of Neutrino Detector for Sterile Neutrino Search at Nuclear Reactors and Nuclear Nonproliferation Applications Open
We describe a new detector, called NuLat, to study electron anti-neutrinos a few meters from a nuclear reactor, and search for anomalous neutrino oscillations. Such oscillations could be caused by sterile neutrinos, and might explain the "…