Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

openocr compti code #12033

Merged
merged 4 commits into from
May 15, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Next Next commit
openocr compti code
  • Loading branch information
Topdu committed Apr 30, 2024
commit 8252de1844055c2a2fae9aa06bba4792bce0f255
169 changes: 169 additions & 0 deletions configs/det/det_repsvtr_db.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,169 @@
Global:
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

配置文件如果都是同一个算法,但是进行大小模型蒸馏,我觉得可以统一放在一个文件夹目录下。比如之前的configd/det/ch_PP-OCRv4/ 把大小模型和蒸馏的配置都放在了一个目录

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

debug: false
use_gpu: true
epoch_num: &epoch_num 500
log_smooth_window: 20
print_batch_step: 100
save_model_dir: ./output/det_repsvtr_db
save_epoch_step: 10
eval_batch_step:
- 0
- 1000
cal_metric_during_train: false
checkpoints:
pretrained_model:
save_inference_dir: null
use_visualdl: false
infer_img: doc/imgs_en/img_10.jpg
save_res_path: ./checkpoints/det_db/predicts_db.txt
distributed: true

Architecture:
model_type: det
algorithm: DB
Transform: null
Backbone:
name: repvit_svtr_det
Neck:
name: RSEFPN
out_channels: 96
shortcut: True
Head:
name: DBHead
k: 50

Loss:
name: DBLoss
balance_loss: true
main_loss_type: DiceLoss
alpha: 5
beta: 10
ohem_ratio: 3

Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001 #(8*8c)
warmup_epoch: 2
regularizer:
name: L2
factor: 5.0e-05

PostProcess:
name: DBPostProcess
thresh: 0.3
box_thresh: 0.6
max_candidates: 1000
unclip_ratio: 1.5

Metric:
name: DetMetric
main_indicator: hmean

Train:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/train_icdar2015_label.txt
ratio_list: [1.0]
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- CopyPaste: null
- IaaAugment:
augmenter_args:
- type: Fliplr
args:
p: 0.5
- type: Affine
args:
rotate:
- -10
- 10
- type: Resize
args:
size:
- 0.5
- 3
- EastRandomCropData:
size:
- 640
- 640
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
total_epoch: *epoch_num
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
total_epoch: *epoch_num
- NormalizeImage:
scale: 1./255.
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
order: hwc
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- threshold_map
- threshold_mask
- shrink_map
- shrink_mask
loader:
shuffle: true
drop_last: false
batch_size_per_card: 8
num_workers: 8

Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data/icdar2015/text_localization/
label_file_list:
- ./train_data/icdar2015/text_localization/test_icdar2015_label.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- DetResizeForTest:
- NormalizeImage:
scale: 1./255.
mean:
- 0.485
- 0.456
- 0.406
std:
- 0.229
- 0.224
- 0.225
order: hwc
- ToCHWImage: null
- KeepKeys:
keep_keys:
- image
- shape
- polys
- ignore_tags
loader:
shuffle: false
drop_last: false
batch_size_per_card: 1
num_workers: 2
profiler_options: null
134 changes: 134 additions & 0 deletions configs/rec/rec_repsvtr_gtc.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,134 @@
Global:
debug: false
use_gpu: true
epoch_num: 200
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/rec_repsvtr_gtc
save_epoch_step: 10
eval_batch_step: [0, 1000]
cal_metric_during_train: False
pretrained_model:
checkpoints:
save_inference_dir:
use_visualdl: false
infer_img: doc/imgs_words/ch/word_1.jpg
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
max_text_length: &max_text_length 25
infer_mode: false
use_space_char: true
distributed: true
save_res_path: ./output/rec/predicts_repsvtr.txt

Optimizer:
name: AdamW
beta1: 0.9
beta2: 0.999
epsilon: 1.e-8
weight_decay: 0.025
no_weight_decay_name: norm
one_dim_param_no_weight_decay: True
lr:
name: Cosine
learning_rate: 0.001 # 8gpus 192bs
warmup_epoch: 5


Architecture:
model_type: rec
algorithm: SVTR_HGNet
Transform:
Backbone:
name: repvit_svtr
Head:
name: MultiHead
head_list:
- CTCHead:
Neck:
name: svtr
dims: 256
depth: 2
hidden_dims: 256
kernel_size: [1, 3]
use_guide: True
Head:
fc_decay: 0.00001
- NRTRHead:
nrtr_dim: 384
max_text_length: *max_text_length
num_decoder_layers: 2

Loss:
name: MultiLoss
loss_config_list:
- CTCLoss:
- NRTRLoss:

PostProcess:
name: CTCLabelDecode

Metric:
name: RecMetric
main_indicator: acc


Train:
dataset:
name: MultiScaleDataSet
ds_width: false
data_dir: ./train_data/
ext_op_transform_idx: 1
label_file_list:
- ./train_data/train_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- RecAug:
- MultiLabelEncode:
gtc_encode: NRTRLabelEncode
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_gtc
- length
- valid_ratio
sampler:
name: MultiScaleSampler
scales: [[320, 32], [320, 48], [320, 64]]
first_bs: &bs 192
fix_bs: false
divided_factor: [8, 16] # w, h
is_training: True
loader:
shuffle: true
batch_size_per_card: *bs
drop_last: true
num_workers: 8
Eval:
dataset:
name: SimpleDataSet
data_dir: ./train_data
label_file_list:
- ./train_data/val_list.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- MultiLabelEncode:
gtc_encode: NRTRLabelEncode
- RecResizeImg:
image_shape: [3, 48, 320]
- KeepKeys:
keep_keys:
- image
- label_ctc
- label_gtc
- length
- valid_ratio
loader:
shuffle: false
drop_last: false
batch_size_per_card: 128
num_workers: 4
Loading
Loading