cherry pick PRs from community (#7273)

* Merge pull request #6824 from ChenNima/release/2.5-kie-save-res

[kie]add write_kie_result to kie infer tool

* Merge pull request #6677 from TonyJiangWJ/release/2.5

修复内存泄露问题

* Update native.cpp (#6650)

fix issue 6640

* Merge pull request #6625 from ynjang/ynjang

update sorted_boxes

* fix DeprecationWarning, (#6604)

DeprecationWarning: The binary mode of fromstring is deprecated, as it behaves surprisingly on unicode inputs. Use frombuffer instead

* Merge pull request #6585 from maxbachmann/release/2.5

replace GPL licensed components

* Merge pull request #6575 from Eling486/release/2.5

update win doc

* Merge pull request #6477 from MikoyChinese/fix-copy-paste

Fix copy_paste no texts augment.

* Merge pull request #6361 from mohamadmansourX/patch-9

Update README_en.md

Co-authored-by: Double_V <liuvv0203@163.com>
Co-authored-by: shawn <1021362695@qq.com>
Co-authored-by: paopjian <672034519@qq.com>

tools/infer/predict_system.py

@@ -120,11 +120,14 @@ def sorted_boxes(dt_boxes):
     _boxes = list(sorted_boxes)
 
     for i in range(num_boxes - 1):
-        if abs(_boxes[i + 1][0][1] - _boxes[i][0][1]) < 10 and \
-                (_boxes[i + 1][0][0] < _boxes[i][0][0]):
-            tmp = _boxes[i]
-            _boxes[i] = _boxes[i + 1]
-            _boxes[i + 1] = tmp
+        for j in range(i, 0, -1):
+            if abs(_boxes[j + 1][0][1] - _boxes[j][0][1]) < 10 and \
+                    (_boxes[j + 1][0][0] < _boxes[j][0][0]):
+                tmp = _boxes[j]
+                _boxes[j] = _boxes[j + 1]
+                _boxes[j + 1] = tmp
+            else:
+                break
     return _boxes
 
 

tools/infer/utility.py

@@ -549,7 +549,7 @@ def text_visual(texts,
 def base64_to_cv2(b64str):
     import base64
     data = base64.b64decode(b64str.encode('utf8'))
-    data = np.fromstring(data, np.uint8)
+    data = np.frombuffer(data, np.uint8)
     data = cv2.imdecode(data, cv2.IMREAD_COLOR)
     return data
 

tools/infer_kie.py

@@ -88,6 +88,29 @@ def draw_kie_result(batch, node, idx_to_cls, count):
     cv2.imwrite(save_path, vis_img)
     logger.info("The Kie Image saved in {}".format(save_path))
 
+def write_kie_result(fout, node, data):
+    """
+    Write infer result to output file, sorted by the predict label of each line.
+    The format keeps the same as the input with additional score attribute.
+    """
+    import json
+    label = data['label']
+    annotations = json.loads(label)
+    max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1)
+    node_pred_label = max_idx.numpy().tolist()
+    node_pred_score = max_value.numpy().tolist()
+    res = []
+    for i, label in enumerate(node_pred_label):
+        pred_score = '{:.2f}'.format(node_pred_score[i])
+        pred_res = {
+                'label': label,
+                'transcription': annotations[i]['transcription'],
+                'score': pred_score,
+                'points': annotations[i]['points'],
+            }
+        res.append(pred_res)
+    res.sort(key=lambda x: x['label'])
+    fout.writelines([json.dumps(res, ensure_ascii=False) + '\n'])
 
 def main():
     global_config = config['Global']
@@ -114,7 +137,7 @@ def main():
 
     warmup_times = 0
     count_t = []
-    with open(save_res_path, "wb") as fout:
+    with open(save_res_path, "w") as fout:
         with open(config['Global']['infer_img'], "rb") as f:
             lines = f.readlines()
             for index, data_line in enumerate(lines):
@@ -139,6 +162,8 @@ def main():
                 node = F.softmax(node, -1)
                 count_t.append(time.time() - st)
                 draw_kie_result(batch, node, idx_to_cls, index)
+                write_kie_result(fout, node, data)
+        fout.close()
     logger.info("success!")
     logger.info("It took {} s for predict {} images.".format(
         np.sum(count_t), len(count_t)))