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

18 Commits (c350bc8b0281eee63b6e61263a7eadaca89a85b2)

Author SHA1 Message Date
yhq 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
Cathy0908 5ac6381758
add error code (#146) 
* add error code
 2022-09-19 16:07:04 +08:00
zzoneee 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
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
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 b2c8f0ef4d
add detection benchmark model ConvViTDet for FastConvMAE (#121) 
* add conv vitdet and modelzoo
 2022-07-18 17:11:41 +08:00
Cathy0908 368378b2af
add Fast ConvMAE (#101) 
* add Fast ConvMAE and Fast ConvMAE benchmark
 2022-07-08 12:11:37 +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 04e26b29cf
add moby swin-tiny pretrained model and benchmark (#72) 2022-05-25 14:19:28 +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
wenmeng zhou aad3835186
fix: add missing shell scripts (#47) 
* add missing scripts
 2022-04-29 17:04:10 +08:00
yhq 04ca0d53c7
Doc/add mae benchmark (#24) 
* add mae large to mae benchmark
* fix dataset pipeline bug  when timm using torhvision original pipeline in mae
* add mae fintune unittest

Co-authored-by: yanhaiqiang.yhq <yanhaiqiang.yhq@gitlab.alibaba-inc.com>
 2022-04-24 14:53:35 +08:00
Cathy0908 13ff8263b3
remove all imports in easycv.utils.__init__ (#21) 2022-04-22 15:22:43 +08:00
Cathy0908 9a3826f0d2
[Feature]: support image visualization for tensorboard and wandb (#15) 
* [Feature]: support image visualization for tensorboard and wandb
 2022-04-21 20:48:58 +08:00
Cathy0908 b1f67f9762
update moby pretrained model to deit small (#10) 
* add auto publish config

* [bugfix]: fix extract.py for benchmarks

* update moby pretrained model to deit small
 2022-04-18 20:39:28 +08:00
Cathy0908 fc4c588147
[bugfix]: fix extract.py for benchmarks (#7) 
* [bugfix]: fix extract.py for benchmarks and add auto publish config

Co-authored-by: jiangnana.jnn <jiangnana.jnn@alibaba-inc.com>
 2022-04-07 17:16:13 +08:00
jiangnana.jnn e8008e3abd [Feature]: uniform input and output format for transforms 2022-04-06 20:02:21 +08:00
wenmeng.zwm 055deba53e initial commit 2022-04-02 20:01:06 +08:00