Merge branch 'dygraph' into fix_doc

doc/doc_ch/whl.md

@@ -36,7 +36,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -69,7 +69,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -114,7 +114,7 @@ for line in result:
 from PIL import Image
 
 image = Image.open(img_path).convert('RGB')
-im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -253,7 +253,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -285,7 +285,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -314,7 +314,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```

doc/doc_en/whl_en.md

@@ -35,7 +35,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -69,7 +69,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -116,7 +116,7 @@ for line in result:
 from PIL import Image
 
 image = Image.open(img_path).convert('RGB')
-im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -262,7 +262,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -292,7 +292,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```
@@ -320,7 +320,7 @@ image = Image.open(img_path).convert('RGB')
 boxes = [line[0] for line in result]
 txts = [line[1][0] for line in result]
 scores = [line[1][1] for line in result]
-im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
+im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/fonts/simfang.ttf')
 im_show = Image.fromarray(im_show)
 im_show.save('result.jpg')
 ```

ppocr/data/simple_dataset.py

@@ -23,6 +23,7 @@ class SimpleDataSet(Dataset):
     def __init__(self, config, mode, logger, seed=None):
         super(SimpleDataSet, self).__init__()
         self.logger = logger
+        self.mode = mode.lower()
 
         global_config = config['Global']
         dataset_config = config[mode]['dataset']
@@ -45,7 +46,7 @@ class SimpleDataSet(Dataset):
         logger.info("Initialize indexs of datasets:%s" % label_file_list)
         self.data_lines = self.get_image_info_list(label_file_list, ratio_list)
         self.data_idx_order_list = list(range(len(self.data_lines)))
-        if mode.lower() == "train":
+        if self.mode == "train" and self.do_shuffle:
             self.shuffle_data_random()
         self.ops = create_operators(dataset_config['transforms'], global_config)
 
@@ -56,16 +57,16 @@ class SimpleDataSet(Dataset):
         for idx, file in enumerate(file_list):
             with open(file, "rb") as f:
                 lines = f.readlines()
-                random.seed(self.seed)
-                lines = random.sample(lines,
-                                      round(len(lines) * ratio_list[idx]))
+                if self.mode == "train" or ratio_list[idx] < 1.0:
+                    random.seed(self.seed)
+                    lines = random.sample(lines,
+                                          round(len(lines) * ratio_list[idx]))
                 data_lines.extend(lines)
         return data_lines
 
     def shuffle_data_random(self):
-        if self.do_shuffle:
-            random.seed(self.seed)
-            random.shuffle(self.data_lines)
+        random.seed(self.seed)
+        random.shuffle(self.data_lines)
         return
 
     def __getitem__(self, idx):
@@ -90,7 +91,10 @@ class SimpleDataSet(Dataset):
                     data_line, e))
             outs = None
         if outs is None:
-            return self.__getitem__(np.random.randint(self.__len__()))
+            # during evaluation, we should fix the idx to get same results for many times of evaluation.
+            rnd_idx = np.random.randint(self.__len__(
+            )) if self.mode == "train" else (idx + 1) % self.__len__()
+            return self.__getitem__(rnd_idx)
         return outs
 
     def __len__(self):