Replies: 2 comments
-
Global:
debug: false
use_gpu: true
epoch_num: 500
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/ch_PP-OCR_V3_det/
save_epoch_step: 10
eval_batch_step:
- 1
cal_metric_during_train: false
pretrained_model: /root/paddlejob/workspace/env_run/liumingda/root/paddlejob/workspace/env_run/liumingda/paddleOCR_work/PaddleOCR-main/models/ch_PP-OCRv3_det_distill_train/best_accuracy.pdparams
checkpoints: null
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:
Backbone:
name: MobileNetV3
scale: 0.5
model_name: large
disable_se: True
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
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
- IaaAugment:
augmenter_args:
- type: Fliplr
args:
p: 0.5
- type: Affine
args:
rotate:
- -10
- 10
- type: Resize
args:
size:
- 0.5
- 3
- EastRandomCropData:
size:
- 960
- 960
max_tries: 50
keep_ratio: true
- MakeBorderMap:
shrink_ratio: 0.4
thresh_min: 0.3
thresh_max: 0.7
- MakeShrinkMap:
shrink_ratio: 0.4
min_text_size: 8
- 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: 4
Eval:
dataset:
name: SimpleDataSet
data_dir: /root/paddlejob/workspace/env_run/liumingda/root/paddlejob/workspace/env_run/liumingda/paddleOCR_work/data/image_50000
label_file_list:
- /root/paddlejob/workspace/env_run/liumingda/root/paddlejob/workspace/env_run/liumingda/paddleOCR_work/data/50000_txt/text/test_copy.txt
transforms:
- DecodeImage:
img_mode: BGR
channel_first: false
- DetLabelEncode: null
- DetResizeForTest: null
- 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 |
Beta Was this translation helpful? Give feedback.
-
根据你的问题描述, 1. 数据集格式检查从你提供的图片来看,数据集格式可能存在问题。请参考以下几点确认数据是否符合 PaddleOCR 的要求:
2. 检查脚本输入参数确保运行
3. 日志输出与调试如果脚本运行没有任何结果,建议检查日志输出或手动添加调试信息:
4. 参考相关讨论根据提供的文档,部分讨论中提到了类似的问题,例如数据集划分无反应或结果未生成。参考以下内容:
5. 系统环境检查根据你的问题背景,还可以检查以下系统环境是否符合 PaddleOCR 的运行需求:
总结请按照以下步骤排查:
如果仍然无法解决问题,可以在相关的 GitHub Discussion 中提供详细的运行环境和错误信息进行反馈。 Response generated by feifei-bot | chatgpt-4o-latest |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
没有结果
数据集格式为
Beta Was this translation helpful? Give feedback.
All reactions