From 0e6ac51a3a644457f81cb34d3ab7721c73ef259a Mon Sep 17 00:00:00 2001
From: wuzekai <3025054974@qq.com>
Date: Tue, 8 Jul 2025 05:35:57 +0000
Subject: [PATCH] Add new file

---
 config/rec_chinese_common_train_v2.0.yml | 106 +++++++++++++++++++++++
 1 file changed, 106 insertions(+)
 create mode 100644 config/rec_chinese_common_train_v2.0.yml

diff --git a/config/rec_chinese_common_train_v2.0.yml b/config/rec_chinese_common_train_v2.0.yml
new file mode 100644
index 0000000..48dd3fe
--- /dev/null
+++ b/config/rec_chinese_common_train_v2.0.yml
@@ -0,0 +1,106 @@
+Global:
+  use_gpu: true
+  epoch_num: 200
+  log_smooth_window: 20
+  print_batch_step: 88
+  save_model_dir: ./output/rec_chinese_common_v2.0
+  save_epoch_step: 500
+  # evaluation is run every 5000 iterations after the 4000th iteration
+  eval_batch_step: [0, 176]
+  cal_metric_during_train: True
+  pretrained_model: ./pretrain_models/ch_ppocr_server_v2.0_rec_train/ch_ppocr_server_v2.0_rec_train/best_accuracy.pdparams
+  checkpoints:
+  save_inference_dir:
+  use_visualdl: false
+  use_wandb: true
+  infer_img: doc/imgs_words/ch/word_1.jpg
+  # for data or label process
+  character_dict_path: ppocr/utils/ppocr_keys_v1.txt
+  max_text_length: 25
+  infer_mode: False
+  use_space_char: True
+  save_res_path: ./output/test/rec/predicts_chinese_common_v2.0.txt
+  name: rec_chinese_common_v2.0
+
+
+Optimizer:
+  name: Adam
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Cosine
+    learning_rate: 0.001
+    warmup_epoch: 5
+  regularizer:
+    name: 'L2'
+    factor: 0.00004
+
+Architecture:
+  model_type: rec
+  algorithm: CRNN
+  Transform:
+  Backbone:
+    name: ResNet
+    layers: 34
+  Neck:
+    name: SequenceEncoder
+    encoder_type: rnn
+    hidden_size: 256
+  Head:
+    name: CTCHead
+    fc_decay: 0.00004
+
+Loss:
+  name: CTCLoss
+
+PostProcess:
+  name: CTCLabelDecode
+
+Metric:
+  name: RecMetric
+  main_indicator: acc
+  ignore_space: True
+  char_precision: True
+  char_recall: True
+  char_f1: True
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/rec/train.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - RecAug: 
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    batch_size_per_card: 256
+    drop_last: True
+    num_workers: 8
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: ./train_data/
+    label_file_list: ["./train_data/rec/val.txt"]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: BGR
+          channel_first: False
+      - CTCLabelEncode: # Class handling label
+      - RecResizeImg:
+          image_shape: [3, 32, 320]
+      - KeepKeys:
+          keep_keys: ['image', 'label', 'length'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 128
+    num_workers: 4
-- 
2.22.0