Hiroto Honda·Dec 12, 2020An unofficial colab walkthrough of Vision TransformerLet’s see how it works by running the codes!A response icon1A response icon1
Hiroto Honda·Jun 4, 2020Digging into Detectron 2 — part 5ROI (Box) HeadA response icon13A response icon13
Hiroto Honda·Mar 10, 2020Digging into Detectron 2 — part 4Region Proposal NetworkA response icon14A response icon14
Hiroto Honda·Feb 7, 2020Digging into Detectron 2 — part 3Data Loader and Ground TruthA response icon2A response icon2
Hiroto Honda·Jan 10, 2020Digging into Detectron 2 (part 2)Feature Pyramid NetworkA response icon5A response icon5
Hiroto Honda·Jan 5, 2020Digging into Detectron 2Part 1: Basic network architecture and repo structureA response icon6A response icon6
Hiroto Honda·May 28, 2019Reproducing training performance of YOLOv3 in PyTorch (Part2)How to assign targets to multi-scale anchorsA response icon1A response icon1
Hiroto Honda·May 16, 2019Survey of Cutting-edge Human Recognition Papers (CVPR’19)We have published a survey blog on cutting-edge human recognition papers that are to be presented at CVPR’19. Enjoy!
Hiroto Honda·Feb 1, 2019Reproducing training performance of YOLOv3 in PyTorch (Part1)Part 1 : Network architecture and channel elements of YOLO layers
Hiroto Honda·Dec 20, 2018Reproducing training performance of YOLOv3 in PyTorch (Part 0)Part 0 : Introduction