cuicheng01
169774a35a
Merge pull request #2381 from cuicheng01/add_finetune_docs
...
update finetune docs
2022-10-17 16:37:15 +08:00
cuicheng01
c4e0662189
update finetune docs
2022-10-17 03:37:24 +00:00
cuicheng01
ea7446e5d8
update finetune docs
2022-10-17 03:31:28 +00:00
gaotingquan
b83da15d27
support set shuffle by config
2022-10-17 11:24:57 +08:00
gaotingquan
d7014129f1
tipc: set DataLoader.Train.sampler.shuffle=False
...
benchmark needs the field to set Global.print_batch_step=1. Check file "./test_tipc/benchmark_train.sh#L76" for details.
2022-10-17 11:24:57 +08:00
HydrogenSulfate
45742397a3
Merge pull request #2374 from HydrogenSulfate/fix_dali
...
add batch Tensor collate to simplify dali code in train/eval/retrival…
2022-10-17 10:40:36 +08:00
cuicheng01
c007cc6bd1
Merge pull request #2016 from TingquanGao/dev/update_imn_model_doc
...
[WIP] update imagenet model doc
2022-10-14 16:18:22 +08:00
cuicheng01
3043923413
Merge pull request #2369 from cuicheng01/add_finetune_docs
...
Add finetune docs
2022-10-13 16:12:06 +08:00
HydrogenSulfate
61b4153907
add batch Tensor collate to simplify dali code in train/eval/retrival code
2022-10-13 12:05:50 +08:00
cuicheng01
51898c6e6c
Merge pull request #2362 from cuicheng01/add_blur_cls
...
[WIP]Add clarity_assessment code
2022-10-12 20:20:22 +08:00
cuicheng01
639dad79a7
Merge pull request #2370 from PaddlePaddle/revert-2368-dev/fix_input_shape
...
Revert "fix: fix input shape to [192, 48]"
2022-10-12 14:12:57 +08:00
Tingquan Gao
4f4c58efec
Revert "fix: fix input shape to [192, 48]"
2022-10-11 22:20:30 +08:00
cuicheng01
c87db7b9e3
update blur code
2022-10-11 13:46:27 +00:00
cuicheng01
623dc4b64a
Merge pull request #2368 from TingquanGao/dev/fix_input_shape
...
fix: fix input shape to [192, 48]
2022-10-11 19:25:32 +08:00
cuicheng01
a9c703fdbc
update finetune.md
2022-10-11 11:21:37 +00:00
cuicheng01
b07a24276f
add finetune.md
2022-10-11 11:16:38 +00:00
gaotingquan
58f5a1376f
fix: fix input shape to [192, 48]
2022-10-10 06:55:17 +00:00
littletomatodonkey
6766ad1672
add more distributed training speed-info ( #2363 )
...
* add more distributed training speed-info
* fix header
2022-10-08 10:29:59 +08:00
cuicheng01
083205273d
add clarity_assessment code
2022-09-29 06:25:22 +00:00
cuicheng01
4438acfda8
Merge pull request #2361 from TingquanGao/dev/tipc_fix_log_path
...
turn off the mkldnn and trt in ConvNeXt infer
2022-09-29 14:07:24 +08:00
gaotingquan
9f64ff6c1c
tipc: turn off mkldnn and trt
...
it will time out when turn on trt or mkldnn
2022-09-29 05:22:44 +00:00
gaotingquan
be434dc66c
tipc: fix the inference model name
2022-09-29 11:16:22 +08:00
gaotingquan
b55791f696
tipc: styling code
2022-09-28 13:33:19 +00:00
gaotingquan
b3ab418e80
refactor: mv the init_res of net to super().__init__()
...
Put the calling of update_res(), stop_after(), freeze_befor() to the construction method of the parent class. And the init_net() support to call stop_after() by config of Arch.
2022-09-28 20:13:19 +08:00
gaotingquan
7513c0b52f
feat: support freeeze subnet
...
freeze subnet specified with the specified layer name by setting OutputTensor.stop_gradient=True
2022-09-28 20:13:19 +08:00
gaotingquan
d670f2e497
rename config file ImageOrientation to PPLCNet_x1_0
2022-09-28 20:01:48 +08:00
gaotingquan
bf91fbfbe4
add warning msg
2022-09-28 20:01:48 +08:00
gaotingquan
75e1291528
debug
2022-09-28 20:01:48 +08:00
gaotingquan
e31509ee81
fix hyperparams & mv to PULC
2022-09-28 20:01:48 +08:00
gaotingquan
19840cb046
refactor: to be pythonic
2022-09-28 20:01:48 +08:00
gaotingquan
e823f17853
feat: support training image orientation model
...
add the config of orientation model
add the preprocess op RandomRot90 that can rotate the img and return the orientation
add the CustomLabelDataset that support getting label by preprocess
refactor some preprocess ops to support dict parameter and return dict
2022-09-28 20:01:48 +08:00
Walter
59a6cfc3e7
Merge pull request #2355 from zengshao0622/shitu_eval
...
add shitu pipeline evaluation
2022-09-28 11:23:54 +08:00
zengshao0622
849406a38c
rename eval file
2022-09-27 13:22:32 +00:00
HydrogenSulfate
db80bfb5ab
change return type from float to Constant when self.learning_rate is an float number
2022-09-27 19:46:20 +08:00
zengshao0622
fc9140c20a
add shitu pipeline evaluation
2022-09-27 09:52:17 +00:00
gaotingquan
0160b8dd0d
fix
2022-09-27 11:56:42 +08:00
gaotingquan
8b3c4f5c65
fix conflict in rebase
2022-09-26 10:15:28 +00:00
gaotingquan
a828503dd8
docs: rm useless
2022-09-26 10:12:28 +00:00
gaotingquan
c45e1c32c5
doc: fix mistakes
2022-09-26 08:08:43 +00:00
gaotingquan
1086e7b918
move to new directory because rebase
2022-09-26 07:59:16 +00:00
littletomatodonkey
e8661fd419
fix distillation link ( #2348 )
2022-09-26 15:35:46 +08:00
gaotingquan
b28fbd0232
docs: fix
2022-09-26 07:30:57 +00:00
gaotingquan
4658e3d9fd
docs: update
2022-09-26 07:30:57 +00:00
gaotingquan
e83c2664f4
docs: update
2022-09-26 07:30:05 +00:00
gaotingquan
60cba5adfa
docs: split
2022-09-26 07:26:34 +00:00
gaotingquan
659e427f32
docs: fix path of config
2022-09-26 07:25:43 +00:00
gaotingquan
f18496291f
docs: fix contents
2022-09-26 07:09:44 +00:00
gaotingquan
dec42bf38b
docs: refactor format of metrics
2022-09-26 07:08:36 +00:00
gaotingquan
5b48958145
add deploy discription
2022-09-26 07:07:06 +00:00
zhengya01
091cb607f6
fix tipc log
2022-09-23 18:53:35 +08:00
