Merge remote-tracking branch 'origin/dygraph' into dygraph

ppocr/utils/utility.py

@@ -49,18 +49,23 @@ def get_check_global_params(mode):
     return check_params
 
 
+def _check_image_file(path):
+    img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif'}
+    return any([path.lower().endswith(e) for e in img_end])
+
+
 def get_image_file_list(img_file):
     imgs_lists = []
     if img_file is None or not os.path.exists(img_file):
         raise Exception("not found any img file in {}".format(img_file))
 
-    img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif', 'GIF'}
-    if os.path.isfile(img_file) and imghdr.what(img_file) in img_end:
+    img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff', 'gif'}
+    if os.path.isfile(img_file) and _check_image_file(img_file):
         imgs_lists.append(img_file)
     elif os.path.isdir(img_file):
         for single_file in os.listdir(img_file):
             file_path = os.path.join(img_file, single_file)
-            if os.path.isfile(file_path) and imghdr.what(file_path) in img_end:
+            if os.path.isfile(file_path) and _check_image_file(file_path):
                 imgs_lists.append(file_path)
     if len(imgs_lists) == 0:
         raise Exception("not found any img file in {}".format(img_file))

ppstructure/docs/quickstart.md

@@ -194,5 +194,6 @@ dict 里各个字段说明如下
 | layout               | 前向中是否执行版面分析                                                                                                                                        | True                                                    |
 | table                | 前向中是否执行表格识别                                                                                                                                        | True                                                    |
 | ocr                  | 对于版面分析中的非表格区域，是否执行ocr。当layout为False时会被自动设置为False                                                                                                  | True                                                    |
+| structure_version                  |      表格结构化模型版本，可选 PP-STRUCTURE。PP-STRUCTURE支持表格结构化模型                                              | PP-STRUCTURE                                                    |
 
 大部分参数和PaddleOCR whl包保持一致，见 [whl包文档](../../doc/doc_ch/whl.md)

ppstructure/docs/quickstart_en.md

@@ -194,5 +194,5 @@ Please refer to: [Documentation Visual Q&A](../vqa/README.md) .
 | layout               | Whether to perform layout analysis in forward                                                                                                                                                                                                                    | True                                                    |
 | table                | Whether to perform table recognition in forward                                                                                                                                                                                                                  | True                                                    |
 | ocr                  | Whether to perform ocr for non-table areas in layout analysis. When layout is False, it will be automatically set to False                                                                                                                                                                                                                 | True                                                    |
-
+| structure_version                     | table structure Model version number, the current model support list is as follows: PP-STRUCTURE support english table structure model | PP-STRUCTURE                 |
 Most of the parameters are consistent with the PaddleOCR whl package, see [whl package documentation](../../doc/doc_en/whl.md)

ppstructure/vqa/tools/eval_with_label_end2end.py

@@ -82,7 +82,7 @@ def polygon_iou(poly1, poly2):
         except shapely.geos.TopologicalError:
             # except Exception as e:
             #     print(e)
-            print('shapely.geos.TopologicalError occured, iou set to 0')
+            print('shapely.geos.TopologicalError occurred, iou set to 0')
             iou = 0
     return iou
 

test_tipc/docs/jeston_test_train_inference_python.md

-# Jeston端基础训练预测功能测试
+# Jetson端基础训练预测功能测试
 
-Jeston端基础训练预测功能测试的主程序为`test_inference_inference.sh`，由于Jeston端CPU较差，Jeston只需要测试TIPC关于GPU和TensorRT预测推理的部分即可。
+Jetson端基础训练预测功能测试的主程序为`test_inference_inference.sh`，由于Jetson端CPU较差，Jetson只需要测试TIPC关于GPU和TensorRT预测推理的部分即可。
 
 ## 1. 测试结论汇总
 
@@ -42,7 +42,7 @@ Jeston端基础训练预测功能测试的主程序为`test_inference_inference.
 
 先运行`prepare.sh`准备数据和模型，然后运行`test_inference_inference.sh`进行测试，最终在```test_tipc/output```目录下生成`python_infer_*.log`格式的日志文件。
 
-`test_inference_inference.sh`仅有一个模式`whole_infer`，在Jeston端，仅需要测试预测推理的模式即可：
+`test_inference_inference.sh`仅有一个模式`whole_infer`，在Jetson端，仅需要测试预测推理的模式即可：
 
 ```
 - 模式3：whole_infer，不训练，全量数据预测，走通开源模型评估、动转静，检查inference model预测时间和精度;
@@ -51,7 +51,7 @@ bash test_tipc/prepare.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_lin
 # 用法1:
 bash test_tipc/test_inference_inference.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer'
 # 用法2: 指定GPU卡预测，第三个传入参数为GPU卡号
-bash test_tipc/test_inference_jeston.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' '1'
+bash test_tipc/test_inference_jetson.sh ./test_tipc/configs/ch_ppocr_mobile_v2.0_det/model_linux_gpu_normal_normal_infer_python_jetson.txt 'whole_infer' '1'
 ```
 
 运行相应指令后，在`test_tipc/output`文件夹下自动会保存运行日志。如`whole_infer`模式下，会运行训练+inference的链条，因此，在`test_tipc/output`文件夹有以下文件：

tools/end2end/eval_end2end.py

@@ -59,7 +59,7 @@ def polygon_iou(poly1, poly2):
         except shapely.geos.TopologicalError:
             # except Exception as e:
             #     print(e)
-            print('shapely.geos.TopologicalError occured, iou set to 0')
+            print('shapely.geos.TopologicalError occurred, iou set to 0')
             iou = 0
     return iou
 

tools/eval.py

@@ -20,8 +20,8 @@ import os
 import sys
 
 __dir__ = os.path.dirname(os.path.abspath(__file__))
-sys.path.append(__dir__)
-sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
+sys.path.insert(0, __dir__)
+sys.path.insert(0, os.path.abspath(os.path.join(__dir__, '..')))
 
 from ppocr.data import build_dataloader
 from ppocr.modeling.architectures import build_model

tools/export_model.py

@@ -133,7 +133,7 @@ def main():
                 else:
                     config["Architecture"]["Models"][key]["Head"][
                         "out_channels"] = char_num
-                # just one final tensor needs to to exported for inference
+                # just one final tensor needs to exported for inference
                 config["Architecture"]["Models"][key][
                     "return_all_feats"] = False
         elif config['Architecture']['Head'][

tools/infer/predict_system.py

@@ -195,7 +195,7 @@ def main(args):
         text_sys.text_detector.autolog.report()
         text_sys.text_recognizer.autolog.report()
 
-    with open(os.path.join(draw_img_save_dir, "system_results.txt"), 'w') as f:
+    with open(os.path.join(draw_img_save_dir, "system_results.txt"), 'w', encoding='utf-8') as f:
         f.writelines(save_results)
 
 

tools/infer/utility.py

@@ -193,7 +193,7 @@ def create_predictor(args, mode, logger):
             gpu_id = get_infer_gpuid()
             if gpu_id is None:
                 logger.warning(
-                    "GPU is not found in current device by nvidia-smi. Please check your device or ignore it if run on jeston."
+                    "GPU is not found in current device by nvidia-smi. Please check your device or ignore it if run on jetson."
                 )
             config.enable_use_gpu(args.gpu_mem, 0)
             if args.use_tensorrt:

tools/infer_e2e.py

@@ -104,7 +104,7 @@ def main():
             preds = model(images)
             post_result = post_process_class(preds, shape_list)
             points, strs = post_result['points'], post_result['texts']
-            # write resule
+            # write result
             dt_boxes_json = []
             for poly, str in zip(points, strs):
                 tmp_json = {"transcription": str}

tools/infer_rec.py

@@ -150,7 +150,7 @@ def main():
                             "label": post_result[key][0][0],
                             "score": float(post_result[key][0][1]),
                         }
-                info = json.dumps(rec_info)
+                info = json.dumps(rec_info, ensure_ascii=False)
             else:
                 if len(post_result[0]) >= 2:
                     info = post_result[0][0] + "\t" + str(post_result[0][1])

tools/infer_vqa_token_ser_re.py

@@ -193,7 +193,7 @@ if __name__ == '__main__':
             result = result[0]
             fout.write(img_path + "\t" + json.dumps(
                 {
-                    "ser_resule": result,
+                    "ser_result": result,
                 }, ensure_ascii=False) + "\n")
             img_res = draw_re_results(img_path, result)
             cv2.imwrite(save_img_path, img_res)