mmdetection

Commit Graph

Author	SHA1	Message	Date
Haian Huang(深度眸)	86c7d8d375	[Enchance] Supplementary notes of sync_random_seed (#7440 ) * Supplementary Notes * update * update * update	3 years ago
Haian Huang(深度眸)	57f63bc0de	[Feature] Add diff seeds to diff ranks. (#7432 )	3 years ago
Haian Huang(深度眸)	c0b2e80ab8	Refactor YOLOX (#6443 ) * Fix aug test error when the number of prediction bboxes is 0 (#6398) * Fix aug test error when the number of prediction bboxes is 0 * test * test * fix lint * Support custom pin_memory and persistent_workers * [Docs] Chinese version of robustness_benchmarking.md (#6375) * Chinese version of robustness_benchmarking.md * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update docs_zh-CN/robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * Update robustness_benchmarking.md * Update robustness_benchmarking.md * Update robustness_benchmarking.md * Update robustness_benchmarking.md * Update robustness_benchmarking.md * Update robustness_benchmarking.md Co-authored-by: RangiLyu <lyuchqi@gmail.com> * update yolox_s * update yolox_s * support dynamic eval interval * fix some error * support ceph * fix none error * fix batch error * replace resize * fix comment * fix docstr * Update the link of checkpoints (#6460) * [Feature]: Support plot confusion matrix. (#6344) * remove pin_memory * update * fix unittest * update cfg * fix error * add unittest * [Fix] Fix SpatialReductionAttention in PVT. (#6488) * [Fix] Fix SpatialReductionAttention in PVT * Add warning * Save coco summarize print information to logger (#6505) * Fix type error in 2_new_data_mode (#6469) * Always map location to cpu when load checkpoint (#6405) * configs: update groie README (#6401) Signed-off-by: Leonardo Rossi <leonardo.rossi@unipr.it> * [Fix] fix config path in docs (#6396) * [Enchance] Set a random seed when the user does not set a seed. (#6457) * fix random seed bug * add comment * enchance random seed * rename Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn> * [BugFixed] fix wrong trunc_normal_init use (#6432) * fix wrong trunc_normal_init use * fix wrong trunc_normal_init use * fix #6446 Co-authored-by: Uno Wu <st9007a@gmail.com> Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it> Co-authored-by: BigDong <yudongwang@tju.edu.cn> Co-authored-by: Haian Huang(深度眸) <1286304229@qq.com> Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn> Co-authored-by: Shusheng Yang <shusheng.yang@qq.com> * bump version to v2.18.1 (#6510) * bump version to v2.18.1 * Update changelog.md * add some comment * fix some comment * update readme * fix lint * add reduce mean * update * update readme * update params Co-authored-by: Cedric Luo <luochunhua1996@outlook.com> Co-authored-by: RangiLyu <lyuchqi@gmail.com> Co-authored-by: Guangchen Lin <347630870@qq.com> Co-authored-by: Andrea Panizza <8233615+AndreaPi@users.noreply.github.com> Co-authored-by: Uno Wu <st9007a@gmail.com> Co-authored-by: Leonardo Rossi <leonardo.rossi@unipr.it> Co-authored-by: BigDong <yudongwang@tju.edu.cn> Co-authored-by: Haobo Yuan <yuanhaobo@whu.edu.cn> Co-authored-by: Shusheng Yang <shusheng.yang@qq.com>	3 years ago
Haian Huang(深度眸)	a7154782f1	Refactor dense_head and speedup (#6268 ) * update get_bboxes * fix decode error * speedup delta2bbox * update others model * fix ms_test * fix unit test * fix ms test * fix yolox error and paa error * fix lint * speedup distance2bbox * fix ci error of dtype * fix docsstr * fix type * fix aug type * rename variable * fix comments * fix type * replace spare with priors * fix rpn * fix comment * fix comment * fix comment	3 years ago
Haian Huang(深度眸)	75238f307e	Refactor one-stage get_bboxes logic (#5317 ) * revert batch to single * update anchor_head * replace preds with bboxes * add point_bbox_coder * FCOS add get_selected_priori * unified anchor-free and anchor-based get_bbox_single * update code * update reppoints and sabl * add sparse priors * add mlvlpointsgenerator * revert __init__ of core * refactor reppoints * delete label channal * add docstr * fix typo * fix args * fix typo * fix doc * fix stride_h * add offset * Unified bbox coder * add offset * remove point_bbox_coder.py * fix docstr * new interface of single_proir * fix device * add unitest * add cuda unitest * add more cuda unintest * fix reppoints * fix device * update all prior * update vfnet * add unintest for ssd and yolo and rename prior_idxs * add docstr for MlvlPointGenerator * update reppoints and rpnhead * add space * add num_base_priors * update some model * update docstr * fixAugFPN test and lint. * Fix autoassign * add docs * Unified fcos decoding * update docstr * fix train error * Fix Vfnet * Fix some * update centernet * revert * add warnings * fix unittest error * delete duplicated * fix comment * fix docs * fix type Co-authored-by: zhangshilong <2392587229zsl@gmail.com>	3 years ago
BigDong	2294badd86	[Feature]SOLO: Segmenting Objects by Locations (#5832 ) * add SOLO * add decoupled SOLO * update decoupled SOLO * fix linting errors * format config filename, config content, loss names, norm_cfg * fix linting errors * fix matrix_nms and configs * Add unit tests for SOLO head * add diceloss * support mmdet-v2+ * add decopledhead * clean Chinese comments * update SOLO * fix * delet debug files * update solo config * fix bug * [Fix]: fix some params cannot get grad * [fix] make sure params can get grad * init commit for resutls * add results and instance results * add docstr * add more unitets * add more unitets * add more unitets * add more unintest * add unitet for instance results * add example * add meta_info_keys results_keys * add modified from * fix unitets * fix typo * add instance seg releated base * forward train for solo * fix simpletest * add docstr * convert to tensor at begin * refactor yolact traing * refactor yolact test * fix test of yolact * fix empty det of yolact * fix return tuple * add format_results * add testfor formatr * solo * add unitest for format_results * add unitest * solo * remove yolact relatede modification * fix zero bbox * fix score size * fix desolo head * update solo head * fix error * rename some attribute * rename some attribute * rename decouple * add doc * format loss * reconer decople * add doc * fix test * fix test * fix doc * remove points nms * refactor the post process * refactor post process of decaouple * refactor base * refactor get_target single * refactor the training of decouple * refactor test of decouple * refactor dice loss * refactor dice * change to format a dict * support detection results in test.py * add base one-stage segmentor * fix doc * add onnx export * add solo config * add dice loss test unit * add solo_head test unit * add more detailed comments * resolve commnets * add test unit * update docstrings and move center of mass to core.utils * add center of mass test unit * resolve comments * resolve commets * fix rle encode * fix results * fix results * abstract dice loss * update docstring * add EPS * add center of mass test unit * add eps parameter * add vis * add nms test unit * configs/ add configs * add desolo light config file * support desolo light head * add desolo light config * add matrix_nms test unit * fix matrix_nms test unit * update matrix doc string * fix error * fix logic error * fix logic error * add comment in test unit * move has_acted to initialization * update solo readme * rename * revert test * fix import in example * fix unitest * add more uintest * add more unites * add more unitest * rename meta to meta_info * fix docstr * fix foc * fix doc * add format_results * fix format results * fix some default value and function name * fix desolo light head error * fix doc and move isntancedata to a new file * fix typo * fix unitest in torch 13 * update matrix nms docstring * fix hard code * add vis * add vis * fix lint * fix doc * fix doc * fix vis * fix vis * fix vis * fix forwardummy doc * fix doc * fix comment * fix doc * fix order of argument * add base one-stage segmentor * fix config files * fix doc * fix doc * support solo * fix error * support solo * rename cls_score * support solo * update model zoo * update docstring * update docstring Co-authored-by: WXinlong <wangxinlon@gmail.com> Co-authored-by: zhangshilong <2392587229zsl@gmail.com>	3 years ago
BigDong	bde7b4b7ee	[Docs] Add header for files (#5900 ) * [Docs] Add header for files * update license copyright * add copyright header * add copyright header tools * delete add header code	3 years ago
Zhiqiang Wang	c181587714	[Feature] Add SyncRandomSizeHook, YOLOXModeSwitchHook and SyncNormHook (#5773 ) * Add yolox_process_hook from yolox-dev * Split the YOLOX Hooks * Fix docs * Applied suggestions from reviewer * Apply suggestions from reviewer * Add docstr and applied suggestions * update * update doc * Applied suggestions about the docs * Fixing docs * Applied suggestions from reviewer * rename * rename and add unittest * fix lint Co-authored-by: PJLAB\huanghaian <1286304229@qq.com>	3 years ago
kellenf	3d91b8b88b	CenterNet(Objects as points) (#4602 ) * flip test ok * clean commit files * rename * merge_master and update * fix wrong merge * add dla34 base * add dla34 * fix details * fix head and add config * update init and config * update config * flip test * Fix error merge * clean model code * refactor loss * rename loss_heatmap to loss_center_heatmap * Fix avg_factor * update dlanet * add find_unused_parameters * Fix warmup_ratio * add unittest * add centernet head docstr. * reduce workers_per_gpu to 4 * fix name error * recode post process * fix flip test * fix flip test error * Refactor post process * Remove DLANet * Remove resnet_ct.py * Add README.md * Add centernet_resnet18_140e_coco.py * Update README.md * Fix comment and docstr * Fix unittest * Fix name and docstr * rename neck * fix comments * fix comments * Stabilize the training process * use default conv init weights * fp16 enabled * udpate readme and add comment * add comment Co-authored-by: hhaAndroid <1286304229@qq.com>	3 years ago
Haian Huang(深度眸)	4310fed1f5	[Feature] Support to visualize results based on prediction quality (#4441 ) * New Add ResultEvaluate * Update ResultVisualizer * Delete debug code * Add Loading related pipeline * 1.Move retrieve_loading_pipeline to dataset.util 2.Support display GT mask 3.Support display GT mask and det mask for visualize fn * Use gt_mask.to_ndarray() * Refactor analyze_results.py * Fix docs str * Logger is silent and add progressBar * Fix lint * Fix docs str and other comment * Fix docs str * Fix docs str * Fix docs str and add unit test for mask2ndarray	4 years ago
Wenwei Zhang	5853fa4aa4	[Refactor]: Clean duplicated reduce mean function (#4056 )	4 years ago
David de la Iglesia Castro	d1cedb72d0	Use mmcv tensor2imgs (#4010 )	4 years ago
Wenwei Zhang	ec7d83bb4c	Refine docs and fix format issues (#3349 ) * Refine docs and fix format issues * reformat * fix mock * Refine format * Reorganize tutorials	4 years ago
Kai Chen	588536de99	Fix docstring formats (#3196 ) * update docstring formats * fix :func: * minor update	4 years ago
Wenwei Zhang	47d663f0fa	Add docstrings of core modules and methods (#3120 ) * Add docstrings of core modules and methods * Update docs and fix comments * Complete docstrings * Resolve comments * reformat docstrings * resolve comments	4 years ago
Wang Xinjiang	4102944d77	Deprecate DistOptimizerHook (#2938 ) * Deprecate DistOptimizerHook * Deprecate DistOptimizerHook * delete DeprecationWarning	4 years ago
kinredon	a9bedfba2e	Fix typos (#2768 )	4 years ago

17 Commits (master)