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

100 Commits (e4722c754fe5eff3f3740d1967fee1305605e5c6)
 

Author SHA1 Message Date
Chen Jiayu e4722c754f
bugfix_common_io (#126) 2022-07-11 19:58:13 +08:00
Chen Jiayu 1e4b2a4001
bugfix_vitdet_predictor (#123) 2022-07-11 14:56:55 +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
Cathy0908 368378b2af
add Fast ConvMAE (#101) 
* add Fast ConvMAE and Fast ConvMAE benchmark
 2022-07-08 12:11:37 +08:00
Cathy0908 e3eaa8b46f
update version (#117) 2022-07-06 18:16:45 +08:00
yhq d06c019d90
Fix/pillow version (#116) 
* modify pillow version
 2022-07-06 12:01:23 +08:00
Cyanyanyan 950f23866d
Update tfrecord_util.py (#111) 
* fix tfrecord read bug
 2022-07-01 18:43:36 +08:00
Cathy0908 6c7f7ad12e
update change_log.md (#109) 
* update change_log.md and README
 2022-07-01 18:41:19 +08:00
Cathy0908 f7f4088152
add visualization doc (#110) 2022-06-30 11:24:52 +08:00
Chen Jiayu 9424cc9660
vitdet visualize and predictor (#102) 
*vitdet bugfix

* support vitdet_predictor
 2022-06-30 09:35:27 +08:00
wenmeng zhou 2885fbf297
relax opencv-python-headless version (#108) 2022-06-23 13:25:25 +08:00
Chen Jiayu 7e56b507f1
vitdet bugfix (#103) 
* vitdet bugfix
 2022-06-22 18:07:44 +08:00
Cathy0908 e09572895b
refactor fp16 (#94) 
* refactor fp16 and fix AMPFP16OptimizerHook
 2022-06-21 16:16:09 +08:00
Yuan, Man 62a1d58f54
Add sailfish for extensible fully sharded data parallel training 2022-06-17 14:10:33 +08:00
yuanman.ym 813a191876 Add sailfish for fully sharded data parallel training 2022-06-17 13:21:27 +08:00
Chen Jiayu 5110de7635
remove RPNHeadNorm, adapted in mmlab_utils (#90) 
* remove  RPNHeadNorm, adapted in mmlab_utils
 2022-06-16 15:53:43 +08:00
Chen Jiayu 0f69dbe902
Swint_cifar config bugfix (#95) 2022-06-16 14:46:47 +08:00
Cathy0908 b737027aa4
remove useless import and optimize imports (#84) 2022-06-13 10:29:41 +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
Cathy0908 04ac412aec
fix num_classes in model of yolox_s_8xb16_300e_voc.py (#88) 2022-06-10 16:51:07 +08:00
Chen Jiayu 57ccd90a23
bugfix_timm_init_weights (#85) 
* bugfix_timm_init_weights
 2022-06-10 12:28:37 +08:00
Cathy0908 859eb9286b
fix metric_learning config (#86) 2022-06-09 11:24:39 +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
Chen Jiayu 12e3bed42b
bugfix_swintiny (#79) 
1. add easycv_model default_path
2. bugfix pretrained
 2022-06-06 12:03:05 +08:00
wenmeng zhou 5bc5cb6f50
fix quick_start.md (#81) 
solve problem in #80
 2022-06-02 16:16:23 +08:00
Chen Jiayu 3ee118f065
Expand cls model zoo (#55) 
1. expand cls model zoo
2. uniform load_pretrained
 2022-06-01 11:01:29 +08:00
Cathy0908 d76d5d79fc
set multiprocess env for speedup (#77) 2022-06-01 10:16:02 +08:00
Cathy0908 4c1b3145e6
[feature] add segmentation modules (#71) 
* add segmentation module & add ResNetV1c & ResNetV1d & add benchmark
 2022-05-31 20:19:17 +08:00
Cathy0908 42d73019e2
update file.md for setting oss config via enviroment variable (#76) 2022-05-30 20:52:00 +08:00
Cathy0908 1614248f31
fix ci_test (#74) 
* fix ci_test and skip test_quantize
 2022-05-27 13:09:21 +08:00
Cathy0908 b66a15a784
add data hub (#70) 
* add data hub
 2022-05-25 17:17:31 +08:00
Cathy0908 04e26b29cf
add moby swin-tiny pretrained model and benchmark (#72) 2022-05-25 14:19:28 +08:00
Cathy0908 106c8224b7
update prepare_data.md (#69) 
* update prepare_data.md
 2022-05-23 20:08:37 +08:00
Xiaohe You 820dcafe28
update yolox compression tutorials (#68) 
* update requirements for model compression
 2022-05-23 14:27:25 +08:00
Cathy0908 00f2e2eb64
fix eval metric during training and add metric unittest (#67) 
* fix eval metric during training and add metric unittest
 2022-05-19 16:07:36 +08:00
Cathy0908 c9a7d02d32
Update prepare_data.md 2022-05-17 18:03:19 +08:00
Cathy0908 4fd29e819b
Update prepare_data.md 2022-05-17 18:02:28 +08:00
Cathy0908 7c29232e79
[bugfix] fix CocoMaskEvaluator missing groundtruth_is_crowd (#61) 
* fix coco evaluation
 2022-05-16 20:21:53 +08:00
Cathy0908 52c2a35784
fix eval.py, remove oss_config from build_dataloader (#62) 2022-05-16 20:21:18 +08:00
Xiaohe You b97908e9cb
ev quantize test update (#64) 2022-05-16 18:40:36 +08:00
Cathy0908 14af96e21d
[feature] add ssl detection benchmark (#58) 
* add ssl detection benchmark
* wrape mmdel model with adding init_weights()
 2022-05-16 15:03:15 +08:00
Cathy0908 ecbfbbb359
fix unittest (#57) 
* fix unittest and skip quantize unittest
 2022-05-16 15:02:12 +08:00
Cathy0908 54d0beb564
update change_log.md (#59) 2022-05-16 14:21:07 +08:00
Cathy0908 f78fa46152
fix citest action (#60) 
* fix citest action
 2022-05-16 11:37:33 +08:00
wenmeng zhou 8af917dc83
update readme.md to changelog 2022-05-13 16:36:54 +08:00
Cathy0908 b5fb2b70c7
[feature]: support mmdet models config (#25) 
* support mmdet models

* add mmlab_models_usage_guide.md

* remove tools/test.py
 2022-05-11 17:44:06 +08:00
Xiaohe You 10266f54a7
update quantize.py code version (#44) 
* compression tutorial

* add details of compression tutorial

* add env of compression tutorial

* update quantize.py code version
 2022-05-07 16:07:07 +08:00
yhq e1ed85f677
Doc/update mae benchmark (#50) 
* update mae benchmark, we fintune the model four times, and chose the highest one as the result. we pretrain and fintune the model only by 8 V100 which is a little different from official one.
 2022-05-05 20:17:03 +08:00
jiangnana.jnn 7f4bf57d25 update version 2022-04-29 17:05:49 +08:00
wenmeng zhou aad3835186
fix: add missing shell scripts (#47) 
* add missing scripts
 2022-04-29 17:04:10 +08:00