249 Commits

Author SHA1 Message Date
yhq
3953bd2bd4
adapt_videopredictor_to_eas (#268) 2023-01-16 14:05:23 +08:00
yhq
8379127388
add video recognition (#256)
* add x3d swin-video clip-bert video algorithm
2023-01-10 17:33:35 +08:00
Cathy0908
d73d89b12b
add inception config and voc config for fcn and upernet (#261)
add inception config and voc config for fcn and upernet
2023-01-04 16:38:45 +08:00
tuofeilun
74cde39e66
Support Single-lens MOT (#258)
Support Single-lens MOT
2023-01-03 16:40:50 +08:00
wenmeng zhou
4fa81beb21
Update README_zh-CN.md 2022-12-12 19:26:04 +08:00
Cathy0908
7f320fcd4d
Update README.md 2022-12-12 19:20:18 +08:00
Cathy0908
028d4afe59
fix mae arg error after timm upgrade (#255) 2022-12-12 11:31:36 +08:00
Cathy0908
56bf3edf4e
fix export ssl models (#257) 2022-12-12 11:31:07 +08:00
tuofeilun
5583101471
bugfix easycv_root and det_test (#253) 2022-12-09 10:10:09 +08:00
Cathy0908
61456a5271
optimize data source with load image (#254) 2022-12-08 16:41:06 +08:00
Cathy0908
7676295e78
update predict.py to support input model directory (#252)
* update predict.py, support model_dir
2022-12-06 18:22:50 +08:00
zzoneee
5c000b6b47
modify the benchmark of deitiii and hydra (#251)
* modify the benchmarks of deitiii and hydra
2022-12-06 16:17:25 +08:00
yhq
14f8a97bdb
Add bevformer benchmark (#249)
* add bev-blancehybrid benchmark
2022-12-06 12:13:09 +08:00
tuofeilun
7ee13097e0
Release v0.8.0 (#250) v0.8.0 2022-12-06 10:52:36 +08:00
Cathy0908
a36948811f
update yolox template config (#243)
* update yolox config templatee

* update oss sync hook,support sync all export  files

* add sync export model config
2022-12-05 22:01:44 +08:00
wenmeng zhou
befb23c2d5
add prediction script (#239)
* add prediction script

* update doc
2022-12-05 18:06:00 +08:00
tuofeilun
3f533ad62e
Release v0.8.0 (#245)
Release v0.8.0
2022-12-05 10:48:48 +08:00
gulou
281ab0b832
fix data_hub error (#248) 2022-12-02 16:06:57 +08:00
tuofeilun
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
gulou
36a3c45efa
add more data source for auto download (#229)
* add caltech, flower, mnist data source

* add det lvis data source

* add pose crowdPose data source

* add pose of OC Human data source

* add pose of mpii data source

* add Seg of voc data source

* add Seg of coco data source

* add Det of wider person datasource

* add Det of african wildlife datasource

* add Det of fruit datasource

* add Det of pet datasource

* add Det of artaxor and tiny person datasource

* add Det of wider face datasource

* add Det of crowd human datasource

* add Det of object365 datasource

* add Seg of coco stuff 10k and 164k datasource

Co-authored-by: Cathy0908 <30484308+Cathy0908@users.noreply.github.com>
2022-12-02 10:57:23 +08:00
tuofeilun
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
tuofeilun
4c88875a0c
support confusion_matrix (#241)
support confusion_matrix
2022-11-29 11:40:57 +08:00
yhq
a9b67f0509
add bevformer benchmark and fix classification predict bug (#240) 2022-11-24 18:25:27 +08:00
Cathy0908
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
k-washi
a36e0e32a4
Fix index of image_scale with y2 with bottom_left implemented in _mosaic_combine (#231) 2022-11-23 19:48:02 +08:00
yhq
7ffff511a5
modify ocr predictor (#237)
* modify ocr predictor
2022-11-22 18:58:55 +08:00
Cathy0908
23ec622270
sync the predict config in the config file (#238) 2022-11-22 17:18:03 +08:00
Jiabei-prog
17c1f39b6f
features/edgevit3 (#214)
* add backbone model 'EdgeVit'
2022-11-17 14:30:12 +08:00
yhq
9809c3b184
update flake8 url for pre-commit (#234) 2022-11-15 13:08:58 +08:00
zzoneee
ab3b2a0258
add Hydra Attention (#220)
* add hydra attention implementation
* refactor deit iii config
2022-11-07 11:19:07 +08:00
yhq
c14c41a0d3
Add mask2former tutorials (#228) 2022-11-07 10:22:46 +08:00
gulou
645fed2d1b
add data source and support for automatic download (#206)
* add data_source imagenet

* modify data_source imagenet and add unittest

* modify data_source imagenet and modify unittest

* modify voc data_source and modify voc unittest and download Part

* modify coco data_source and modify coco unittest and  add download Part , modify voc data_source

* add dataset metadata Format specification

* add pose download data , modify coco.py and modiy download file function ,add test coco download a part

* modify download file function

* modify download of cifar10 and cifar100

* modify dataset_name  to target_dir

* create download_util and modify function

* modify function

* modify function

* add test case , modify

* modify something

* modify something

* modify something

* modify something

* modify something

* modify something

* add wget

* add wget

* modify

* add new modify

* add new modify

* modify something

* modify something and add something

* modify something and add something

* modify something and add something

* modify something and add something

* modify something and add something

* modify test case

* modify test case

* modify test case

* modify test case

* modify test case
2022-11-04 19:36:37 +08:00
Cathy0908
bf6debfc4f
add release note for 0.7.0 (#226)
* add release note for 0.7.0
v0.7.0
2022-11-03 15:58:13 +08:00
Cathy0908
55c9d8d270
modify citest to install package (#223)
* modify citest from source code to install
2022-11-03 11:53:18 +08:00
tuofeilun
8fa2f6ea40
Support NNI hpo (#211)
* support hpo using NNI
2022-11-01 15:28:16 +08:00
Cathy0908
5f75b22438
move test model to nfs (#222) 2022-11-01 12:09:33 +08:00
Cathy0908
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
Cathy0908
39673768f7
Fix predictor with numpy and PIL input (#221)
* fix predictor with numpy and PIL imput
2022-11-01 10:47:38 +08:00
zouxinyi0625
f19a05a536
fix yolox export error when output is empty (#217)
* fix yolox export error when output is empty
2022-10-28 10:26:53 +08:00
wenmeng zhou
8e3bf8c0dd
update readme (#218) 2022-10-27 19:09:31 +08:00
yhq
00aa7c2f79
Support_mask2former_semantic (#199)
* add mask2former semantic branch
2022-10-26 17:23:21 +08:00
zouxinyi0625
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
Cathy0908
54e9571423
add BEVFormer (#203)
* add BEVFormer and benchmark
2022-10-24 17:20:12 +08:00
wenmeng zhou
90fee5bf6b
Merge pull request #207 from alibaba/merge_master_internal_22021012
Merge master internal 22021012
2022-10-19 10:31:59 +08:00
wenmeng zhou
f58d249d11
avoid unnecessarily loading backbone weights from url for predictor (#212) 2022-10-14 17:42:07 +08:00
jiangnana.jnn
cb86523179 Merge branch 'merge_master_internal_22021012' of github.com:alibaba/EasyCV into merge_master_internal_22021012 2022-10-12 13:37:10 +08:00
jiangnana.jnn
2a92f67ac2 fix code check 2022-10-12 13:29:13 +08:00
Cathy0908
05578f76a9
Merge branch 'master' into merge_master_internal_22021012 2022-10-12 12:00:41 +08:00
wenmeng zhou
1e1afbfd0e
fix: import YoloxPredictor (#205)
* import yoloxpredictor
2022-10-12 11:32:26 +08:00
jiangnana.jnn
10c2545875 Merge branch 'master_internal_22021012' into merge_master_internal_22021012 2022-10-12 11:24:08 +08:00