software . 2020

ultralytics/yolov5: v3.1 - Bug Fixes and Performance Improvements

Jocher, Glenn; Stoken, Alex; Borovec, Jirka; NanoCode012; ChristopherSTAN; Changyu, Liu; Laughing; Tkianai; Hogan, Adam; Lorenzomammana; ...
Open Source
  • Published: 29 Oct 2020
  • Publisher: Zenodo
Abstract
<p>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 (<code>inplace</code> fields for nn.Hardswish() activations) for native PyTorch 1.7.0 compatibility.</p> Breaking Changes <ul> <li>'GIoU' hyperparameter has been renamed to 'box' to better reflect a criteria-agnostic regression loss term (<a href="https://github.com/ultralytics/yolov5/pull/1120">https://github.com/ultralytics/yolov5/pull/1120</a>)</li> </ul> Bug Fixes <ul> <li>PyTorch 1.7 compatibility update. <code>torch&gt;=1....
Download fromView all 3 versions
Zenodo
Software . 2020
Provider: Datacite
Zenodo
Software . 2020
Provider: Datacite
Zenodo
Software . 2020
Provider: Zenodo
Any information missing or wrong?Report an Issue