📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.
Add the show of the inference time to the web
SWHL75786513b8aa
diff --git a/assets/ocrweb_time.jpg b/assets/ocrweb_time.jpgnew file mode 100644index 0000000..6a45011Binary files /dev/null and b/assets/ocrweb_time.jpg differdiff --git a/ocrweb/README.md b/ocrweb/README.mdindex 9db5067..5cf834d 100755--- a/ocrweb/README.md+++ b/ocrweb/README.md@@ -1,3 +1,18 @@+### 相关问题+1. 各个阶段使用的模型有哪些?+ 可以从`task.py`中看到+ ```python+ det_model_path = 'resources/models/ch_PP-OCRv2_det_infer.onnx'+ cls_model_path = 'resources/models/ch_ppocr_mobile_v2.0_cls_infer.onnx'+ rec_model_path = 'resources/models/ch_ppocr_mobile_v2.0_rec_infer.onnx'+ ```+2. 网页上显示的推理时间可以具体解释一下吗?+ <div align="center">+ <img src="../assets/ocrweb_time.jpg" width="80%" height="80%">+ </div>+3. OCR各个阶段的参数值都从哪里可以看到?+ - 从各个阶段的目录下对应类的初始化函数可以看到+### 运行1. 安装`requirements.txt`下相关包```shell@@ -11,7 +26,7 @@```shellpython main.py```-4. 打开`http://127.0.0.1:9005/`,即可+4. 打开`http://127.0.0.1:9003/`,即可### 目录结构```textdiff --git a/ocrweb/main.py b/ocrweb/main.pyindex 3752c09..a7f198c 100644--- a/ocrweb/main.py+++ b/ocrweb/main.py@@ -26,9 +26,12 @@ def ocr():if request.method == 'POST':url_get = request.get_json()url_get = str(url_get).split(',')[1]+image = base64.b64decode(url_get)nparr = np.frombuffer(image, np.uint8)image = cv2.imdecode(nparr, cv2.IMREAD_COLOR)+ if image.ndim == 2:+ image = cv2.cvtColor(image, cv2.COLOR_GRAY2BGR)return detect_recognize(image)diff --git a/ocrweb/resources/ch_ppocr_mobile_v2_cls/text_cls.py b/ocrweb/resources/ch_ppocr_mobile_v2_cls/text_cls.pyindex e6974ca..c283561 100644--- a/ocrweb/resources/ch_ppocr_mobile_v2_cls/text_cls.py+++ b/ocrweb/resources/ch_ppocr_mobile_v2_cls/text_cls.py@@ -76,6 +76,7 @@ class TextClassifier(object):return img_listdef __call__(self, image_dir):+ elapse = 0if isinstance(image_dir[0], (list, str)):img_list = self.load_image(image_dir)else:@@ -83,16 +84,17 @@ class TextClassifier(object):img_list = copy.deepcopy(img_list)img_num = len(img_list)+# Calculate the aspect ratio of all text barswidth_list = []for img in img_list:width_list.append(img.shape[1] / float(img.shape[0]))+# Sorting can speed up the cls processindices = np.argsort(np.array(width_list))cls_res = [['', 0.0]] * img_numbatch_num = self.cls_batch_num- elapse = 0for beg_img_no in range(0, img_num, batch_num):end_img_no = min(img_num, beg_img_no + batch_num)norm_img_batch = []@@ -112,7 +114,6 @@ class TextClassifier(object):prob_out = self.session.run(None, onnx_inputs)[0]cls_result = self.postprocess_op(prob_out)- elapse += time.time() - starttimefor rno in range(len(cls_result)):label, score = cls_result[rno]@@ -120,6 +121,8 @@ class TextClassifier(object):if '180' in label and score > self.cls_thresh:img_list[indices[beg_img_no + rno]] = cv2.rotate(img_list[indices[beg_img_no + rno]], 1)++ elapse += time.time() - starttimereturn img_list, cls_res, elapsediff --git a/ocrweb/resources/ch_ppocr_mobile_v2_det/text_detect.py b/ocrweb/resources/ch_ppocr_mobile_v2_det/text_detect.pyindex 32673be..b6f9f51 100644--- a/ocrweb/resources/ch_ppocr_mobile_v2_det/text_detect.py+++ b/ocrweb/resources/ch_ppocr_mobile_v2_det/text_detect.py@@ -94,7 +94,7 @@ class TextDetector(object):return pointsdef filter_tag_det_res(self, dt_boxes, image_shape):- img_height, img_width = image_shape[0:2]+ img_height, img_width = image_shape[:2]dt_boxes_new = []for box in dt_boxes:box = self.order_points_clockwise(box)@@ -107,17 +107,11 @@ class TextDetector(object):dt_boxes = np.array(dt_boxes_new)return dt_boxes- def filter_tag_det_res_only_clip(self, dt_boxes, image_shape):- img_height, img_width = image_shape[0:2]- dt_boxes_new = []- for box in dt_boxes:- box = self.clip_det_res(box, img_height, img_width)- dt_boxes_new.append(box)- dt_boxes = np.array(dt_boxes_new)- return dt_boxes-def __call__(self, img):- ori_im = img.copy()+ starttime = time.time()++ ori_shape = img.shape[:2]+data = {'image': img}data = transform(data, self.preprocess_op)img, shape_list = data@@ -127,13 +121,13 @@ class TextDetector(object):img = img.astype(np.float32)shape_list = np.expand_dims(shape_list, axis=0)- starttime = time.time()preds = self.session.run([self.output_name],{self.input_name: img})post_result = self.postprocess_op(preds[0], shape_list)dt_boxes = post_result[0]['points']- dt_boxes = self.filter_tag_det_res(dt_boxes, ori_im.shape)+ dt_boxes = self.filter_tag_det_res(dt_boxes, ori_shape)+elapse = time.time() - starttimereturn dt_boxes, elapsediff --git a/ocrweb/resources/ch_ppocr_mobile_v2_rec/text_recognize.py b/ocrweb/resources/ch_ppocr_mobile_v2_rec/text_recognize.pyindex 54aece6..fa827e9 100644--- a/ocrweb/resources/ch_ppocr_mobile_v2_rec/text_recognize.py+++ b/ocrweb/resources/ch_ppocr_mobile_v2_rec/text_recognize.py@@ -86,21 +86,23 @@ class TextRecognizer(object):return img_listdef __call__(self, image_dir):+ elapse = 0if not isinstance(image_dir, list):img_list = self.load_image(image_dir)else:img_list = image_dirimg_num = len(img_list)+# Calculate the aspect ratio of all text barswidth_list = []for img in img_list:width_list.append(img.shape[1] / float(img.shape[0]))+# Sorting can speed up the recognition processindices = np.argsort(np.array(width_list))rec_res = [['', 0.0]] * img_numbatch_num = self.rec_batch_num- elapse = 0for beg_img_no in range(0, img_num, batch_num):end_img_no = min(img_num, beg_img_no + batch_num)norm_img_batch = []diff --git a/ocrweb/resources/rapidOCR.py b/ocrweb/resources/rapidOCR.pyindex 2b4ef83..cc396f0 100644--- a/ocrweb/resources/rapidOCR.py+++ b/ocrweb/resources/rapidOCR.py@@ -2,6 +2,7 @@# -*- encoding: utf-8 -*-import copyfrom pathlib import Path+import timeimport cv2import numpy as np@@ -46,7 +47,9 @@ class TextSystem(object):cls_model_path=None) -> None:super(TextSystem).__init__()self.text_detector = TextDetector(det_model_path)+self.text_recognizer = TextRecognizer(rec_model_path)+self.use_angle_cls = use_angle_clsif self.use_angle_cls:self.text_classifier = TextClassifier(cls_model_path)@@ -105,79 +108,39 @@ class TextSystem(object):_boxes[i + 1] = tmpreturn _boxes- @staticmethod- def load_image(image_path):- img, flag = check_and_read_gif(image_path)- if not flag:- img = cv2.imread(image_path)- if img is None:- raise ValueError(f"error in loading image:{image_path}")- return img-- def __call__(self, image_path):- # img = self.load_image(image_path)- img = image_path- dt_boxes, elapse = self.text_detector(img)- print("dt_boxes num : {}, elapse : {}".format(- len(dt_boxes), elapse))+ def __call__(self, img):+ dt_boxes, det_elapse = self.text_detector(img)+ print(f"dt_boxes num: {len(dt_boxes)}, elapse: {det_elapse}")if dt_boxes is None or dt_boxes.size == 0:return None, None, img- img_crop_list = []+ start_time = time.time()+ img_crop_list = []dt_boxes = self.sorted_boxes(dt_boxes)-for bno in range(len(dt_boxes)):tmp_box = copy.deepcopy(dt_boxes[bno])img_crop = self.get_rotate_crop_image(img, tmp_box)img_crop_list.append(img_crop)+ crop_elapse = time.time() - start_time+if self.use_angle_cls:- img_crop_list, angle_list, elapse = self.text_classifier(- img_crop_list)- print("cls num : {}, elapse : {}".format(- len(img_crop_list), elapse))-- rec_res, elapse = self.text_recognizer(img_crop_list)- print("rec_res num : {}, elapse : {}".format(- len(rec_res), elapse))- # self.print_draw_crop_rec_res(img_crop_list, rec_res)+ img_crop_list, _, cls_elapse = self.text_classifier(img_crop_list)+ print(f"cls num : {len(img_crop_list)}, elapse: {cls_elapse}")++ rec_res, rec_elapse = self.text_recognizer(img_crop_list)+ print(f"rec_res num: {len(rec_res)}, elapse: {rec_elapse}")++ start_time = time.time()filter_boxes, filter_rec_res = [], []for box, rec_reuslt in zip(dt_boxes, rec_res):text, score = rec_reusltif score >= drop_score:filter_boxes.append(box)filter_rec_res.append(rec_reuslt)- return filter_boxes, filter_rec_res, img---if __name__ == '__main__':- # 文本检测+方向分类+文本识别-- # v1.0- # from ch_ppocr_mobile_v1_det import TextDetector-- # v2.0 超轻量- # from ch_ppocr_mobile_v2_cls import TextClassifier- # from ch_ppocr_mobile_v2_det import TextDetector- # from ch_ppocr_mobile_v2_rec import TextRecognizer-- # det_model_path = 'models/ch_ppocr_mobile_v2_det_train.onnx'- # cls_model_path = 'models/ch_ppocr_mobile_v2.0_cls_train.onnx'- # rec_model_path = 'models/ch_ppocr_mobile_v2.0_rec_pre.onnx'-- # v2.0 通用模型- from ch_ppocr_server_v2_det import TextDetector- from ch_ppocr_server_v2_rec import TextRecognizer-- from ch_ppocr_mobile_v2_cls import TextClassifier-- det_model_path = 'models/ch_ppocr_server_v2.0_det_train.onnx'- cls_model_path = 'models/ch_ppocr_mobile_v2.0_cls_train.onnx'- rec_model_path = 'models/ch_ppocr_server_v2.0_rec_pre.onnx'-- image_path = r'test_images/long1.jpg'+ filter_elapse = time.time() - start_time- text_sys = TextSystem(det_model_path, rec_model_path,- use_angle_cls=True,- cls_model_path=cls_model_path)- dt_boxes, rec_res = text_sys(image_path)- visualize(image_path, dt_boxes, rec_res)+ elapse_part = [f'{det_elapse:.4f}',+ f'{(cls_elapse+crop_elapse):.4f}',+ f'{(rec_elapse+filter_elapse):.4f}'+ ]+ return filter_boxes, filter_rec_res, img, elapse_partdiff --git a/ocrweb/task.py b/ocrweb/task.pyindex 19f9312..4a43a2f 100644--- a/ocrweb/task.py+++ b/ocrweb/task.py@@ -1,19 +1,20 @@# !/usr/bin/env python# -*- encoding: utf-8 -*--# @File: worker.py+# @File: task.py# @Time: 2021/03/07 20:29:32-# @Author: Max+# @Author: SWHL+# @Contact: [email protected]import base64+from functools import reduceimport jsonimport timeimport cv2import numpy as np-from resources.rapidOCR import TextSystem, draw_text_det_res+from resources.rapidOCR import TextSystem, draw_text_det_res, check_and_read_gif-# 实例化模型-det_model_path = 'resources/models/ch_ppocr_server_v2.0_det_infer.onnx'+det_model_path = 'resources/models/ch_PP-OCRv2_det_infer.onnx'cls_model_path = 'resources/models/ch_ppocr_mobile_v2.0_cls_infer.onnx'rec_model_path = 'resources/models/ch_ppocr_mobile_v2.0_rec_infer.onnx'@@ -28,10 +29,10 @@ def detect_recognize(image_path):image = cv2.imread(image_path)elif isinstance(image_path, np.ndarray):image = image_path+ else:+ raise TypeError(f'{image_path} is not str or ndarray.')- t1 = time.time()- dt_boxes, rec_res, img = text_sys(image)- t2 = time.time()+ dt_boxes, rec_res, img, elapse_part = text_sys(image)if dt_boxes is None or rec_res is None:temp_rec_res = []@@ -39,6 +40,7 @@ def detect_recognize(image_path):indent=2,ensure_ascii=False)elapse = 0+ elapse_part = ''image = cv2.imencode('.jpg', img)[1]img = str(base64.b64encode(image))[2:-1]else:@@ -54,7 +56,9 @@ def detect_recognize(image_path):image = cv2.imencode('.jpg', det_im)[1]img = str(base64.b64encode(image))[2:-1]- elapse = f'{t2-t1:.3f}'+ elapse = reduce(lambda x, y: float(x)+float(y), elapse_part)+ elapse_part = ','.join([str(x) for x in elapse_part])return json.dumps({'image': img,- 'elapse': elapse,+ 'total_elapse': f'{elapse:.4f}',+ 'elapse_part': elapse_part,'rec_res': rec_res_data})diff --git a/ocrweb/templates/index.html b/ocrweb/templates/index.htmlindex c70c8e8..f37d1e7 100644--- a/ocrweb/templates/index.html+++ b/ocrweb/templates/index.html@@ -8,8 +8,9 @@</head><body><h1 align="center">- RapidOCR Demo - <a href="https://github.com/RapidAI/RapidOCR" style="font-size: 14px;">欢迎Star</a>+ <b><i>Rapid🗲OCR Demo</i></b> + <a href="https://github.com/RapidAI/RapidOCR" style="font-size: 14px;">欢迎Star</a> + <a href="https://github.com/RapidAI/RapidOCR/tree/main/ocrweb#readme" style="font-size:14px">了解Demo</a></h1><div class='area'><span class="uplodNote">图片文件类型支持PNG、JPG、JPEG、BMP,图片大小不超过3M。</span>@@ -26,7 +27,7 @@<div class="rightarea" id="recogDiv"><span id="rec_res" class="span_title">文本识别结果</span>- <br/> <br/>+ <br/><br/><table id="locTable" class="table" cellspacing="0" cellpadding="5"></table></div></div>@@ -86,15 +87,27 @@$("#detect_img").attr('src', 'data:image/jpeg;base64,'+ data['image']);$('#detect_img').show();}- if (data["elapse"]){- document.getElementById("rec_res").textContent = "文本识别结果(耗时:" + String(data['elapse']) + "s)"++ if (data["total_elapse"]){+ document.getElementById("rec_res").textContent = "文本识别结果(Total:" + String(data["total_elapse"]) + "s)"$("#rec_res").show();}+if (data["rec_res"]){var rec_res = JSON.parse(data["rec_res"]);- // 绘制整个结果表格+ console.log(data['elapse_part']);+ if (data['elapse_part']){+ var elapse_list = data['elapse_part'].split(',');+ }else{+ var elapse_list = [0, 0, 0];+ }var data = "";+ data += "<tr>" ++ '<th align="right">Det: ' + elapse_list[0] + 's</th>' ++ '<th align="center">Cls: ' + elapse_list[1] + 's</th>' ++ '<th align="left">Rec: ' + elapse_list[2] + 's</th>' ++ "</tr>"data += "<tr>" +'<th bgcolor="#C0C0C0">序号</th>' +'<th bgcolor="#C0C0C0">识别结果</th>' +