mirror of
https://github.com/PaddlePaddle/PaddleOCR.git
synced 2025-06-03 21:53:39 +08:00
75d16610f4
* Update PP-OCRv4_introduction.md * Update PP-OCRv4_introduction.md (#10616) * Update PP-OCRv4_introduction.md * Update PP-OCRv4_introduction.md * Update PP-OCRv4_introduction.md * Update README.md * Cherrypicking GH-10217 and GH-10216 to PaddlePaddle:Release/2.7 (#10655) * Don't break overall processing on a bad image * Add preprocessing common to OCR tasks Add preprocessing to options * Update requirements.txt (#10656) added missing pyyaml library * [TIPC]update xpu tipc script (#10658) * fix-typo (#10642) Co-authored-by: Dennis <dvorst@users.noreply.github.com> Co-authored-by: shiyutang <34859558+shiyutang@users.noreply.github.com> * 修改数据增强导致的DSR报错 (#10662) (#10681) * 修改数据增强导致的DSR报错 * 错误修改回滚 * Update algorithm_overview_en.md (#10670) Fixed simple spelling errors. * Implement recoginition method ParseQ * Document update for new recognition method ParseQ * add prediction for parseq * Update rec_vit_parseq.yml * Update rec_r31_sar.yml * Update rec_r31_sar.yml * Update rec_r50_fpn_srn.yml * Update rec_vit_parseq.py * Update rec_vit_parseq.yml * Update rec_parseq_head.py * Update rec_img_aug.py * Update rec_vit_parseq.yml * Update __init__.py * Update predict_rec.py * Update paddleocr.py * Update requirements.txt * Update utility.py * Update utility.py --------- Co-authored-by: xiaoting <31891223+tink2123@users.noreply.github.com> Co-authored-by: topduke <784990967@qq.com> Co-authored-by: dyning <dyning.2003@163.com> Co-authored-by: UserUnknownFactor <63057995+UserUnknownFactor@users.noreply.github.com> Co-authored-by: itasli <ilyas.tasli@outlook.fr> Co-authored-by: Kai Song <50285351+USTCKAY@users.noreply.github.com> Co-authored-by: dvorst <87502756+dvorst@users.noreply.github.com> Co-authored-by: Dennis <dvorst@users.noreply.github.com> Co-authored-by: shiyutang <34859558+shiyutang@users.noreply.github.com> Co-authored-by: Dec20B <1192152456@qq.com> Co-authored-by: ncoffman <51147417+ncoffman@users.noreply.github.com>
117 lines
2.4 KiB
YAML
117 lines
2.4 KiB
YAML
Global:
|
|
use_gpu: True
|
|
epoch_num: 20
|
|
log_smooth_window: 20
|
|
print_batch_step: 5
|
|
save_model_dir: ./output/rec/parseq
|
|
save_epoch_step: 3
|
|
# evaluation is run every 5000 iterations after the 4000th iteration
|
|
eval_batch_step: [0, 500]
|
|
cal_metric_during_train: True
|
|
pretrained_model:
|
|
checkpoints:
|
|
save_inference_dir:
|
|
use_visualdl: False
|
|
infer_img: doc/imgs_words_en/word_10.png
|
|
# for data or label process
|
|
character_dict_path: ppocr/utils/dict/parseq_dict.txt
|
|
character_type: en
|
|
max_text_length: 25
|
|
num_heads: 8
|
|
infer_mode: False
|
|
use_space_char: False
|
|
save_res_path: ./output/rec/predicts_parseq.txt
|
|
|
|
|
|
Optimizer:
|
|
name: Adam
|
|
beta1: 0.9
|
|
beta2: 0.999
|
|
lr:
|
|
name: OneCycle
|
|
max_lr: 0.0007
|
|
|
|
Architecture:
|
|
model_type: rec
|
|
algorithm: ParseQ
|
|
in_channels: 3
|
|
Transform:
|
|
Backbone:
|
|
name: ViTParseQ
|
|
img_size: [32, 128]
|
|
patch_size: [4, 8]
|
|
embed_dim: 384
|
|
depth: 12
|
|
num_heads: 6
|
|
mlp_ratio: 4
|
|
in_channels: 3
|
|
Head:
|
|
name: ParseQHead
|
|
# Architecture
|
|
max_text_length: 25
|
|
embed_dim: 384
|
|
dec_num_heads: 12
|
|
dec_mlp_ratio: 4
|
|
dec_depth: 1
|
|
# Training
|
|
perm_num: 6
|
|
perm_forward: true
|
|
perm_mirrored: true
|
|
dropout: 0.1
|
|
# Decoding mode (test)
|
|
decode_ar: true
|
|
refine_iters: 1
|
|
|
|
Loss:
|
|
name: ParseQLoss
|
|
|
|
PostProcess:
|
|
name: ParseQLabelDecode
|
|
|
|
Metric:
|
|
name: RecMetric
|
|
main_indicator: acc
|
|
is_filter: True
|
|
|
|
Train:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir:
|
|
transforms:
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- ParseQRecAug:
|
|
aug_type: 0 # or 1
|
|
- ParseQLabelEncode:
|
|
- SVTRRecResizeImg:
|
|
image_shape: [3, 32, 128]
|
|
padding: False
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
|
|
loader:
|
|
shuffle: True
|
|
batch_size_per_card: 192
|
|
drop_last: True
|
|
num_workers: 4
|
|
|
|
Eval:
|
|
dataset:
|
|
name: LMDBDataSet
|
|
data_dir:
|
|
transforms:
|
|
- DecodeImage: # load image
|
|
img_mode: BGR
|
|
channel_first: False
|
|
- ParseQLabelEncode: # Class handling label
|
|
- SVTRRecResizeImg:
|
|
image_shape: [3, 32, 128]
|
|
padding: False
|
|
- KeepKeys:
|
|
keep_keys: ['image', 'label', 'length']
|
|
loader:
|
|
shuffle: False
|
|
drop_last: False
|
|
batch_size_per_card: 384
|
|
num_workers: 4
|