028d4afe59
fix mae arg error after timm upgrade ( #255 )
2022-12-12 11:31:36 +08:00
14f8a97bdb
Add bevformer benchmark ( #249 )
...
* add bev-blancehybrid benchmark
2022-12-06 12:13:09 +08:00
654554cf65
support obj365 ( #242 )
...
Support Objects365 pretrain and Adding the DINO++ model can achieve an accuracy of 63.4mAP at a model scale of 200M(Under the same scale, the accuracy is the best)
2022-12-02 14:33:01 +08:00
23f2b0e399
Adapt designer ( #235 )
...
1. Use original config as startup script. (For details, see refactor config parsing method #225 )
2. Refactor the splicing rules of the check_base_cfg_path function in the EasyCV/easycv/utils/config_tools.py
3. Support three ways to pass class_list parameter.
4. Fix the bug that clsevalutor may make mistakes when evaluating top5.
5. Fix the bug that the distributed export cannot export the model.
6. Fix the bug that the load pretrained model key does not match.
7. support cls data source itag.
2022-12-01 17:47:10 +08:00
a9b67f0509
add bevformer benchmark and fix classification predict bug ( #240 )
2022-11-24 18:25:27 +08:00
f8c9a9a1c9
Improve the performance of bevformer ( #224 )
...
Improve the performance of bevformer
* add hybrid brach (#232 )
Co-authored-by: yhq <yanhaiqiang.yhq@alibaba-inc.com>
2022-11-23 21:32:08 +08:00
17c1f39b6f
features/edgevit3 ( #214 )
...
* add backbone model 'EdgeVit'
2022-11-17 14:30:12 +08:00
ab3b2a0258
add Hydra Attention ( #220 )
...
* add hydra attention implementation
* refactor deit iii config
2022-11-07 11:19:07 +08:00
7f08eb6b3f
merge internal master 20221027 ( #216 )
...
* avoid numpy version check when xtcocotools can be imported
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10377599
* * move thirdparty into easycv
* fix code style
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10395748
* move thirdparty into easycv
* fix missing thirdparty/deformable_attention/src when build package
* optimize ci_test
* update version to 0.6.3.8
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10412059
* update version to 0.6.3.8
* fix face keypoints bugs in FT
* update version to 0.6.3.9
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10443200
* update version to 0.6.3.9
* fix import thirdparty
* fix unittest
* fix unittest
Co-authored-by: wenmeng.zwm <wenmeng.zwm@alibaba-inc.com>
Co-authored-by: shouzhou.bx <shouzhou.bx@alibaba-inc.com>
2022-11-01 10:48:12 +08:00
00aa7c2f79
Support_mask2former_semantic ( #199 )
...
* add mask2former semantic branch
2022-10-26 17:23:21 +08:00
8a484e88fd
Add yolox jit script model end2end support ( #215 )
...
* add yolox jit script model end2end support
* update export.md
2022-10-26 15:09:05 +08:00
54e9571423
add BEVFormer ( #203 )
...
* add BEVFormer and benchmark
2022-10-24 17:20:12 +08:00
10c2545875
Merge branch 'master_internal_22021012' into merge_master_internal_22021012
2022-10-12 11:24:08 +08:00
0a796ec2f1
更改mask2former接口，适配maas
...
Link: https://code.alibaba-inc.com/pai-vision/EasyCV/codereview/10292532
* modify postprocess
* Merge remote-tracking branch 'remotes/origin/master' into mask2former_postprocessing
# Conflicts:
# tests/ut_config.py
* assert the output value
* add mask2former models to data/test/xxx/models
* fixed train
2022-09-30 15:31:58 +08:00
513e0d060a
remove unused dependency ( #204 )
...
* remove unused dependency
2022-09-30 11:26:36 +08:00
397ecf2658
Feature/paddleocr inference ( #148 )
...
* add ocr model and convert weights from paddleocrv3
2022-09-28 14:03:16 +08:00
608949b936
Merge branch 'master_github'
2022-09-20 19:59:05 +08:00
f9566c7027
fix face 2d keypoints devices bug
2022-09-20 16:10:23 +08:00
bb53e066be
fix missing vit model ( #197 )
...
* fix missing vit model
* set pretrained false while export cls model
2022-09-19 19:52:21 +08:00
5ac6381758
add error code ( #146 )
...
* add error code
2022-09-19 16:07:04 +08:00
ad78dfd3a1
fix DeiTIII cr bug ( #196 )
...
* fixbug_DeiTIII and rename vit_transfomer_dynamic.py to vit_transformer_dynamic.py
2022-09-17 11:21:47 +08:00
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
1d5edf6d78
Merge pull request #191 from alibaba/easycv_internal_0830
...
merge internal version into github master
2022-09-14 15:32:46 +08:00
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
bf43e8a25b
merge github master
2022-09-08 10:38:31 +08:00
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
4104bbea88
bug_fix:missing utils ( #183 )
...
* add init.py
2022-09-02 18:39:18 +08:00
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
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
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
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
3c6c2c0b6f
add mask2former algo ( #115 )
...
add mask2former algo
support panopitc pipeline
add segment predictor
2022-08-08 18:17:01 +08:00
9517bb80ff
add dn_detr algo ( #119 )
...
support dn-detr-r50: 44.39
refactor set_criterion
2022-07-27 15:06:06 +08:00
8c93caa2d9
support Efficientformer algo ( #128 )
...
* add efficientformer
2022-07-27 11:36:03 +08:00
fe081c8aba
add torchacc, support swin ( #105 )
...
* add torchacc, support swin
2022-07-27 10:22:44 +08:00
b2c8f0ef4d
add detection benchmark model ConvViTDet for FastConvMAE ( #121 )
...
* add conv vitdet and modelzoo
2022-07-18 17:11:41 +08:00
eeabb4c6ab
refactor det ( #124 )
2022-07-13 12:11:40 +08:00
5fb0a86f69
support fcos ( #100 )
...
support fcos(38.57)
2022-07-12 18:07:02 +08:00
6b8b04db72
add upernet algo ( #118 )
...
* add upernet algo
* fix import onnx bug
2022-07-12 11:14:09 +08:00
0b472bacf1
refactor detection, support detr and dab-detr ( #104 )
...
refactor detection, support detr and dab-detr
2022-07-11 14:52:49 +08:00
368378b2af
add Fast ConvMAE ( #101 )
...
* add Fast ConvMAE and Fast ConvMAE benchmark
2022-07-08 12:11:37 +08:00
e09572895b
refactor fp16 ( #94 )
...
* refactor fp16 and fix AMPFP16OptimizerHook
2022-06-21 16:16:09 +08:00
5110de7635
remove RPNHeadNorm, adapted in mmlab_utils ( #90 )
...
* remove RPNHeadNorm, adapted in mmlab_utils
2022-06-16 15:53:43 +08:00
0f69dbe902
Swint_cifar config bugfix ( #95 )
2022-06-16 14:46:47 +08:00
b737027aa4
remove useless import and optimize imports ( #84 )
2022-06-13 10:29:41 +08:00
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
57ccd90a23
bugfix_timm_init_weights ( #85 )
...
* bugfix_timm_init_weights
2022-06-10 12:28:37 +08:00
3af93bdac5
YOLOX End2end & Blade Support ( #66 )
...
* support export with jit.trace and jit.script and end2end
2022-06-08 20:41:15 +08:00
12e3bed42b
bugfix_swintiny ( #79 )
...
1. add easycv_model default_path
2. bugfix pretrained
2022-06-06 12:03:05 +08:00
3ee118f065
Expand cls model zoo ( #55 )
...
1. expand cls model zoo
2. uniform load_pretrained
2022-06-01 11:01:29 +08:00
Cathy0908
yhq
tuofeilun
Jiabei-prog
zzoneee
zouxinyi0625
jiangnana.jnn
tianchu.gtc
wenmeng.zwm
shouzhou.bx
wuziheng
pengyu.lpy