修改LaTeXOCR的数据处理部分，将生成的数据集中的绝对路径改为相对路径 (#13702)

* test

* dataprocess_abspath2relpath

configs/rec/rec_latex_ocr.yml

@@ -69,6 +69,7 @@ Metric:
 Train:
   dataset:
     name: LaTeXOCRDataSet
+    data_dir: ./train_data/LaTeXOCR/train
     data: ./train_data/LaTeXOCR/latexocr_train.pkl
     min_dimensions: [32, 32]
     max_dimensions: [672, 192]
@@ -99,6 +100,7 @@ Train:
 Eval:
   dataset:
     name: LaTeXOCRDataSet
+    data_dir: ./train_data/LaTeXOCR/val
     data: ./train_data/LaTeXOCR/latexocr_val.pkl
     min_dimensions: [32, 32]
     max_dimensions: [672, 192]

docs/algorithm/formula_recognition/algorithm_rec_latex_ocr.en.md

@@ -63,7 +63,7 @@ Evaluation:
 # Validation set evaluation
 python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams
 # Test set evaluation
-python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams Eval.dataset.data=./train_data/LaTeXOCR/latexocr_test.pkl
+python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams Eval.dataset.data_dir=./train_data/LaTeXOCR/test Eval.dataset.data=./train_data/LaTeXOCR/latexocr_test.pkl
 ```
 
 Prediction:

docs/algorithm/formula_recognition/algorithm_rec_latex_ocr.md

@@ -71,7 +71,7 @@ python3 tools/train.py -c configs/rec/rec_latex_ocr.yml -o Global.eval_batch_ste
 # 验证集评估
 python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams
 # 测试集评估
-python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams Eval.dataset.data=./train_data/LaTeXOCR/latexocr_test.pkl
+python3 tools/eval.py -c configs/rec/rec_latex_ocr.yml -o Global.pretrained_model=./rec_latex_ocr_train/best_accuracy.pdparams Eval.dataset.data_dir=./train_data/LaTeXOCR/test Eval.dataset.data=./train_data/LaTeXOCR/latexocr_test.pkl
 ```
 
 ### 3.4 预测

ppocr/data/latexocr_dataset.py

@@ -42,6 +42,7 @@ class LaTeXOCRDataSet(Dataset):
         loader_config = config[mode]["loader"]
 
         pkl_path = dataset_config.pop("data")
+        self.data_dir = dataset_config["data_dir"]
         self.min_dimensions = dataset_config.pop("min_dimensions")
         self.max_dimensions = dataset_config.pop("max_dimensions")
         self.batchsize = dataset_config.pop("batch_size_per_pair")
@@ -128,7 +129,8 @@ class LaTeXOCRDataSet(Dataset):
 
             images_transform = []
 
-            for img_path in ims:
+            for file_name in ims:
+                img_path = os.path.join(self.data_dir, file_name)
                 data = {
                     "img_path": img_path,
                 }

ppocr/utils/formula_utils/math_txt2pkl.py

@@ -44,6 +44,7 @@ def txt2pickle(images, equations, save_dir):
             ):
                 divide_h = math.ceil(height / 16) * 16
                 divide_w = math.ceil(width / 16) * 16
+                im = os.path.basename(im)
                 data[(divide_w, divide_h)].append((eqs[indices[i]], im))
         data = dict(data)
         with open(save_p, "wb") as file: