4digit_training done

trainer/dataset.py

@@ -121,6 +121,9 @@ def hierarchical_dataset(root, opt, select_data='/'):
     print(dataset_log)
     dataset_log += '\n'
     for dirpath, dirnames, filenames in os.walk(root+'/'):
+        print(f"dirpath : {dirpath}")
+        print(f"dirnames : {dirnames}")
+
         if not dirnames:
             select_flag = False
             for selected_d in select_data:
@@ -146,7 +149,7 @@ class OCRDataset(Dataset):
         self.root = root
         self.opt = opt
         print(root)
-        self.df = pd.read_csv(os.path.join(root,'labels.csv'), sep='^([^,]+),', engine='python', usecols=['filename', 'words'], keep_default_na=False)
+        self.df = pd.read_csv(os.path.join(root,'labels.csv'), sep='^([^,]+),',dtype={'words': str}, engine='python', usecols=['filename', 'words'], keep_default_na=False)
         self.nSamples = len(self.df)
 
         if self.opt.data_filtering_off:
@@ -159,7 +162,7 @@ class OCRDataset(Dataset):
                     if len(label) > self.opt.batch_max_length:
                         continue
                 except:
-                    print(label)
+                    print(f"type of label {type(label)} \n {label}")
                 out_of_char = f'[^{self.opt.character}]'
                 if re.search(out_of_char, label.lower()):
                     continue