gaotingquan
|
2a61ac65bf
|
debug
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
ac27cb1917
|
debug
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
9e683d0d69
|
debug
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
106ff27010
|
debug
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
428edb6ff8
|
debug for infer
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
58daf805a9
|
debug
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
c30df63035
|
support Static
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
392b75b1ac
|
revert for running
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
9beb154bc3
|
support ShiTu
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
d3374e897e
|
revert for running
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
32593b6375
|
refactor
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
d3941dc1e9
|
rm amp code from train and eval & use decorator for amp training
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
5a6fe171a7
|
refactor: rm train and eval from engine
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
187f38ebdd
|
refactor
1. rm Global.eval_mode
2. add Global.task
3. mv type_name to ppcls.utils
4. build dataloader, loss, metric by mode
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
73e2cde617
|
mv some attrs to __init__()
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
0d7e595fc7
|
mv model_saver to __init__()
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
6e77bd6cd5
|
rm codes for compatibility with old version
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
f525cea006
|
replace the arg engine with config
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
0e28a39da3
|
refactor
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
fad5c8e348
|
refactor: simpfy engine.train()
1. ModelSaver();
2. _build_ema_model();
3. _init_checkpoints();
4. others.
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
a38e42f644
|
refactor: iter_per_epoch -> max_iter
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
284e2a6756
|
refactor: mv all dataloaders to engine.dataloader_dict
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
6bed0f5707
|
refactor: build_train_func & build_eval_func
1. rm engine.device and use paddle.device.get_device() instead;
2. mv some code to build_train_func or build_eval_func to simpfy engine.
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
75a20ba557
|
refactor: add ClassModel to unify model forward interface
|
2023-03-10 16:56:55 +08:00 |
|
gaotingquan
|
376d83d46e
|
refactor: simplify engine
|
2023-03-10 16:56:55 +08:00 |
tianyi1997
|
f313a6d873
|
Support training without amp
|
2023-02-28 15:01:21 +08:00 |
|
tianyi1997
|
a9b8432597
|
fix: wrong base class & simplify train func
|
2023-02-28 15:01:21 +08:00 |
|
tianyi1997
|
ac466b68da
|
Create MetaBNNeck
|
2023-02-28 15:01:21 +08:00 |
|
tianyi1997
|
21e76d08b6
|
Modify codes based on reviews
|
2023-02-28 15:01:21 +08:00 |
|
tianyi1997
|
d79fb66e19
|
Create train func & cfg for MetaBIN
|
2023-02-28 15:01:21 +08:00 |
HydrogenSulfate
|
fb763b7096
|
fix(dali): reset dataloader manually when using DALI dataloader during epoch training
|
2023-02-21 20:11:04 +08:00 |
zengshao0622
|
1c68b63a66
|
fix some nots
|
2023-02-15 12:00:55 +08:00 |
|
HydrogenSulfate
|
4fdcda7c60
|
fix bug in randaug, train_progressive and efficientnet_v2
|
2023-01-31 21:15:22 +08:00 |
|
HydrogenSulfate
|
7e12c73e0a
|
polish progressive training code
|
2023-01-31 21:15:22 +08:00 |
|
HydrogenSulfate
|
3a8b56801d
|
feat(model): add EfficientNetV2 code and fix AttrDict BUG
|
2023-01-31 21:15:22 +08:00 |
|
gaotingquan
|
81de331e00
|
rename to re_parameterize() for re-parameterization nets
|
2023-01-06 20:29:07 +08:00 |
zh-hike
|
4292c1a90d
|
fix turtle import bug
|
2023-01-06 10:57:05 +08:00 |
|
HydrogenSulfate
|
b05c8b1b7e
|
fix(retrieval): remove max_iter in retrieval.py to avoid empty data
|
2023-01-05 18:44:22 +08:00 |
|
HydrogenSulfate
|
2f331d8588
|
use scipy.sparse to speed up local query expansion
|
2023-01-05 15:13:04 +08:00 |
|
HydrogenSulfate
|
6871d601ff
|
speed up local QE by sparse matmul
|
2023-01-05 15:13:04 +08:00 |
|
HydrogenSulfate
|
c6865e255e
|
refactor(retrieval): polish retrieval.py
|
2023-01-05 15:13:04 +08:00 |
|
HydrogenSulfate
|
97f99cd826
|
refactor(retrieval): polish retrieval.py
|
2023-01-05 15:13:04 +08:00 |
|
zh-hike
|
f8978a2f0c
|
修改cifar100参数配置
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
d8f049ae76
|
增加代码规范，删除无用空格
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
f073e97d22
|
增加cifar100参数yaml
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
009f347d64
|
修改空格等代码规范
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
692b8d8c1f
|
增加data的代码复用及RecModel的修改，代码已跑通
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
4db132444d
|
增加RecModel配合WideResNet代码以及参数转换成RecModel
|
2023-01-04 13:42:00 +08:00 |
|
zh-hike
|
7823f340b1
|
cifar10_4000跑出论文精度代码
|
2023-01-04 13:42:00 +08:00 |
|
HydrogenSulfate
|
97398d9f12
|
fix export pretrained_model when it is None
|
2022-12-16 18:46:21 +08:00 |