2 Commits (f54e5603fd0702c24a5a5019ee7b39e9208a752e)

Author	SHA1	Message	Date
Nioolek	07ab35222c	[Feature] Support YOLOv8 training (#458) ... * add v8 training head * add training config * update * update1 * update all config * update all config * update metafile * add head loss * update readme * iou2ciou in tal, add config * change init layer * update * update * add clip_grad * update max_aspect_ratio * add init * fix aug config * update forward * add official v8 loss * add official v8 loss * 同步预测方式 * fix loss bug * delete useless code * 替换iou，但还有问题 * fix bug * fix empty * add UT * add UT * update readme * replace iou_cal * add use_ciou docstr * update metafile * update metafile * update metafile Co-authored-by: huanghaian <huanghaian@sensetime.com> Co-authored-by: hha <1286304229@qq.com>	2023-01-18 14:16:37 +08:00
HinGwenWoong	935d710f79	[Feature] Support YOLOv8 inference (#445) ... * Add backbone * Improve code * fix * Add neck * Add config * Fix layer param * Fix layer param * Add head * Add head * Add model converter * Add model converter * Add model converter * Improve code * update * update * align test * Improve code * Improve code * Improve code * Fix lint * Fix lint * Fix lint * Fix lint * Improve code * Improve code * Improve code * Add configs * Improve doc * Improve doc * update * Fix config * update * Fix config * Fix config * update * Fix config epoch * update * Fix docstr * Add UT * Add UT * Fix doc * update * Fix lint * Fix doc * Fix config name * Improve config * Improve default * Add docstr * Improve code * Improve code * Drop `bbox_head.head_module.dfl.conv.weight` when convert to mmyolo weight * Delete useless code * Add batch_shapes_cfg but not enable it. * update Co-authored-by: huanghaian <huanghaian@sensetime.com>	2023-01-11 19:01:06 +08:00