mirrors
/
EasyCV
mirror of https://github.com/alibaba/EasyCV.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
197 Commits
29 Branches
19 Tags
16 MiB
Commit Graph

71 Commits (e7b69a8f631dee8c64b1fede0c64b52fdcf77bcf)

Author SHA1 Message Date
jiangnana.jnn c6bb2479ef add BEVFormer 2022-09-28 17:13:14 +08:00
yhq 397ecf2658
Feature/paddleocr inference (#148) 
* add ocr model and convert weights from paddleocrv3
 2022-09-28 14:03:16 +08:00
Cathy0908 bb68fcbf5c
fix test_prun oom (#202) 2022-09-28 12:47:11 +08:00
jiangnana.jnn 893d879b44 Merge branch 'github_master' 2022-09-23 15:10:22 +08:00
Cathy0908 7a89d1b7b8
refactor yolox predictor, support batch inference (#198) 
* update yolox predictor
 2022-09-23 13:51:06 +08:00
jiangnana.jnn 061d9f7ff8 fix unittest for test_prune 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10201563

    * fix unittest for test_prune
 2022-09-21 14:38:58 +08:00
Cathy0908 5dfe7b2898
update some predcitors, support batch inference (#195) 
update some predcitors, support batch inference
 2022-09-20 10:04:42 +08:00
Cathy0908 5ac6381758
add error code (#146) 
* add error code
 2022-09-19 16:07:04 +08:00
tuofeilun 9f01a37ad4
Refactor ViTDet backbone and simple feature pyramid (#177) 
1. The vitdet backbone implemented by d2 is about 20% faster than the vitdet backbone originally reproduced by easycv.
2. 50.57 -> 50.65
 2022-09-16 11:03:53 +08:00
wenmeng zhou 1d5edf6d78
Merge pull request #191 from alibaba/easycv_internal_0830 
merge internal version into github master
 2022-09-14 15:32:46 +08:00
zzoneee 0cb91de0cb
add DeiT III (#171) 
1.Add a backbone: deitiii.
2.Add an optimizer: lamb. 
3.Add a sampler: RASampler. 
4.Add a lr update hook: CosineAnnealingWarmupByEpochLrUpdaterHook.
5.In easycv/models/classification/classification.py, I remove the default mixup_cfg to keep the classification.py clean.
 2022-09-14 15:24:54 +08:00
Cathy0908 7301f8c7b6
fix io.copytree (#193) 2022-09-14 12:04:52 +08:00
wenmeng.zwm 0de3bc1521 fix test_case 2022-09-08 21:55:13 +08:00
wenmeng.zwm bf43e8a25b merge github master 2022-09-08 10:38:31 +08:00
wenmeng.zwm 962a057f4c [to 43878396] fix conflict with mmdet when using EasyCV 
when adapt for mmlab, the original modules will be changed,  which will make argument error when using mmdet original config and interface
1.  add interface for removing adaptation for mmlab
2.  register copy of mmlab module into easycv
3.  bump internal version to 0.6.3.1

Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10059050
 2022-09-08 09:55:18 +08:00
zouxinyi0625 9ad1a8f448
Fix YOLOX-Edge problem and update yolox-pai turtorial (#182) 
* complete yolox introduction

* fix env problem with nni2.6.1

* fix yolox-edge problem

*  add docker turtorial

* add blade test

* support old export yolox model

Co-authored-by: wuziheng <zhoulou.wzh@alibaba-inc.com>
 2022-09-06 17:11:12 +08:00
jiangnana.jnn 4ecc9fcc41 fix LoadImage 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9978695

    * fix LoadImage
 2022-09-01 11:50:17 +08:00
shouzhou.bx befe6d8c8f update face 2d keypoint predictor pipeline 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9969788
 2022-08-31 18:52:32 +08:00
tuofeilun b198c5a81f
support DINO algo (#144) 
dino_4sc_r50_12e：48.71
dino_4sc_r50_24e：50.53
dino_4sc_r50_36e：50.69
dino_4sc_swinl_12e: 56.86
dino_4sc_swinl_36e: 58.04
dino_5sc_swinl_36e: 58.47
 2022-08-31 15:18:11 +08:00
liangting.zl a5988732cc feat: add hand keypoints predictor 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9935447

    * feat: add hand keypoints predictor
 2022-08-31 10:25:05 +08:00
jiangnana.jnn 778d0ec43c fix mmlab utils 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9943746

    * fix mmlab utils
 2022-08-30 14:06:30 +08:00
jiangnana.jnn 1acef39f8a update face predictor 
* update FaceKeypointsPredictor
 * update face config
        Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9932947

    * update FaceKeypointsPredictor
 2022-08-29 20:06:18 +08:00
tuofeilun e3678fbbfa
FCOS update torch_style (#170) 
fcos update torch style
 2022-08-29 16:21:14 +08:00
shouzhou.bx c221b22791 【bug fix】 fix data argumentaion bug 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9907176
 2022-08-27 10:07:11 +08:00
tuofeilun 6821cdc9db
refactor detection predictor (#158) 
The use of unified DetrPredictor for detection test and predictor.
 2022-08-26 10:28:17 +08:00
jiangnana.jnn f78b08954f update to_ms_config 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9897512

    * update to_ms_config
 2022-08-25 16:57:56 +08:00
shouzhou.bx 2e8fc44dc1 add face-2d-keypoints 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9809249

    * add face 2d keypoint config
 2022-08-25 16:57:37 +08:00
jiangnana.jnn bc64851614 update to_ms_config 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9891090

    * update to_ms_config
 2022-08-25 15:31:57 +08:00
liangting.zl 2bf7c9f6ff 新增coco-wholebody-hand数据集，新增pck auc epe nme评价指标 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9790242
 2022-08-24 19:19:33 +08:00
wuziheng 9aaa600f79
Yolox improve with REPConv/ASFF/TOOD (#154) 
* add attention layer and more loss function

* add attention layer and various loss functions

* add siou loss

* add tah,various attention layers, and different loss functions

* add asff sim, gsconv

* blade utils fit faster

* blade optimize for yolox static & fp16

* decode output for yolox control by cfg

* add reparameterize_models for export

* e2e trt_nms plugin export support and numeric test

* split preprocess from end2end+blade, speedup from 17ms->7.2ms

Co-authored-by: zouxinyi0625 <zouxinyi.zxy@alibaba-inc.com>
 2022-08-24 18:11:15 +08:00
jiangnana.jnn 0f74adb848 add predict pipeline 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9828601

    * add predict pipeline
 2022-08-23 19:52:52 +08:00
jiangnana.jnn b3abdf507f fix unittest 
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/9809645

    * fix unittest
 2022-08-19 15:12:13 +08:00
pengyu.lpy 0128e881d9 add segformer algo 
* 将COCO_Stuff_164k数据集增加到了data_hub.md, prepared_data.md, 以及将其对应脚本加到了prepare_data文件夹下面

* 增加了segformer对应的predictor

* 完善docs/source/model_zoo_seg.md中关于segformer的信息
 2022-08-18 10:40:18 +08:00
Cathy0908 a11f200ec3
refactor `get_sample` to `__getitem__` for all datasources api (#156) 
* refactor `get_sample` to `__getitem__` for all datasources api

* fix MMpad config
 2022-08-17 14:24:17 +08:00
Cathy0908 f5cea32405
fix datasource cache (#153) 2022-08-10 19:51:32 +08:00
yhq 3c6c2c0b6f
add mask2former algo (#115) 
add mask2former algo
support panopitc pipeline
add segment predictor
 2022-08-08 18:17:01 +08:00
Cathy0908 ef698811cb
remove "get_length" function in data spurces (#140) 2022-08-03 17:30:35 +08:00
Chen Jiayu 9517bb80ff
add dn_detr algo (#119) 
support dn-detr-r50: 44.39
refactor set_criterion
 2022-07-27 15:06:06 +08:00
Chen Jiayu 8c93caa2d9
support Efficientformer algo (#128) 
* add efficientformer
 2022-07-27 11:36:03 +08:00
Cathy0908 fe081c8aba
add torchacc, support swin (#105) 
* add torchacc, support swin
 2022-07-27 10:22:44 +08:00
zouxinyi0625 f2266bc634
Fix yolox detector prediction (#125) 
* fix export error

Co-authored-by: zxy <zxy@B-X0GHLVDL-0414.local>
 2022-07-14 12:23:57 +08:00
Chen Jiayu eeabb4c6ab
refactor det (#124) 2022-07-13 12:11:40 +08:00
Chen Jiayu 5fb0a86f69
support fcos (#100) 
support fcos(38.57)
 2022-07-12 18:07:02 +08:00
yhq 6b8b04db72
add upernet algo (#118) 
* add upernet algo
* fix import onnx bug
 2022-07-12 11:14:09 +08:00
Chen Jiayu 0b472bacf1
refactor detection, support detr and dab-detr (#104) 
refactor detection, support detr and dab-detr
 2022-07-11 14:52:49 +08:00
Cyanyanyan 950f23866d
Update tfrecord_util.py (#111) 
* fix tfrecord read bug
 2022-07-01 18:43:36 +08:00
Chen Jiayu 9424cc9660
vitdet visualize and predictor (#102) 
*vitdet bugfix

* support vitdet_predictor
 2022-06-30 09:35:27 +08:00
yuanman.ym 813a191876 Add sailfish for fully sharded data parallel training 2022-06-17 13:21:27 +08:00
Chen Jiayu e61488d319
Support ViTDet algo (#35) 
* adapt mmlab modules
* add vitdet
* support conv aggregation
* modify vitdet load pretrained
* support fp16
* modify defaultformatbundle
* modify aug
* bugfix sampler
* bugfix mmresize
* bugfix fp16&nonetype
* bugfix filterannotation
* support dlc
* bugfix dist
* bugfix detsourcecoco
* smodify mmdet_parse_losses
* bugfix nan
* bugfix eval
* bugfix data=nonetype
* modify resize_embed
* support vitdet_conv
* add vitdet_conv init_weight
* add test_vitdet
* uniform rand_another
* uniform use fp16 method
* add test_fp16

Co-authored-by: jiangnana.jnn <jiangnana.jnn@alibaba-inc.com>
 2022-06-10 21:49:32 +08:00
zouxinyi0625 3af93bdac5
YOLOX End2end & Blade Support (#66) 
* support export with jit.trace and jit.script and end2end
 2022-06-08 20:41:15 +08:00