modify hubserving
This commit is contained in:
dyning
parent
5155ac03a1
commit
72dbeee87c
|
|
@ -0,0 +1,109 @@
|
|||
# 服务部署
|
||||
|
||||
PaddleOCR提供2种服务部署方式：
|
||||
- 基于HubServing的部署：已集成到PaddleOCR中（[code](https://github.com/PaddlePaddle/PaddleOCR/tree/develop/deploy/ocr_hubserving)），按照本教程使用；
|
||||
- 基于PaddleServing的部署：详见PaddleServing官网[demo](https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/ocr)，后续也将集成到PaddleOCR。
|
||||
|
||||
服务部署目录下包括检测、识别、2阶段串联三种服务包，根据需求选择相应的服务包进行安装和启动。目录如下：
|
||||
```
|
||||
deploy/hubserving/
|
||||
└─ ocr_det 检测模块服务包
|
||||
└─ ocr_rec 识别模块服务包
|
||||
└─ ocr_system 检测+识别串联服务包
|
||||
```
|
||||
|
||||
每个服务包下包含3个文件。以2阶段串联服务包为例，目录如下：
|
||||
```
|
||||
deploy/hubserving/ocr_system/
|
||||
└─ __init__.py 空文件
|
||||
└─ config.json 配置文件，启动服务时作为参数传入
|
||||
└─ module.py 主模块，包含服务的完整逻辑
|
||||
```
|
||||
|
||||
## 启动服务
|
||||
以下步骤以检测+识别2阶段串联服务为例，如果只需要检测服务或识别服务，替换相应文件路径即可。
|
||||
### 1. 安装paddlehub
|
||||
```pip3 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple```
|
||||
|
||||
### 2. 安装服务模块
|
||||
PaddleOCR提供3种服务模块，根据需要安装所需模块。如：
|
||||
|
||||
安装检测服务模块：
|
||||
```hub install deploy/hubserving/ocr_det/```
|
||||
|
||||
或，安装识别服务模块：
|
||||
```hub install deploy/hubserving/ocr_rec/```
|
||||
|
||||
或，安装检测+识别串联服务模块：
|
||||
```hub install deploy/hubserving/ocr_system/```
|
||||
|
||||
### 3. 修改配置文件
|
||||
在config.json中指定模型路径、是否使用GPU、是否对结果做可视化等参数，如，串联服务ocr_system的配置：
|
||||
```python
|
||||
{
|
||||
"modules_info": {
|
||||
"ocr_system": {
|
||||
"init_args": {
|
||||
"version": "1.0.0",
|
||||
"det_model_dir": "./inference/det/",
|
||||
"rec_model_dir": "./inference/rec/",
|
||||
"use_gpu": true
|
||||
},
|
||||
"predict_args": {
|
||||
"visualization": false
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
其中，模型路径对应的模型为```inference模型```。
|
||||
|
||||
### 4. 运行启动命令
|
||||
```hub serving start -m ocr_system --config hubserving/ocr_det/config.json```
|
||||
|
||||
这样就完成了一个服务化API的部署，默认端口号为8866。
|
||||
|
||||
**NOTE:** 如使用GPU预测(即，config中use_gpu置为true)，则需要在启动服务之前，设置CUDA_VISIBLE_DEVICES环境变量，如：```export CUDA_VISIBLE_DEVICES=0```，否则不用设置。
|
||||
|
||||
## 发送预测请求
|
||||
配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果:
|
||||
|
||||
```python
|
||||
import requests
|
||||
import json
|
||||
import cv2
|
||||
import base64
|
||||
|
||||
def cv2_to_base64(image):
|
||||
return base64.b64encode(image).decode('utf8')
|
||||
|
||||
# 发送HTTP请求
|
||||
data = {'images':[cv2_to_base64(open("./doc/imgs/11.jpg", 'rb').read())]}
|
||||
headers = {"Content-type": "application/json"}
|
||||
# url = "http://127.0.0.1:8866/predict/ocr_det"
|
||||
# url = "http://127.0.0.1:8866/predict/ocr_rec"
|
||||
url = "http://127.0.0.1:8866/predict/ocr_system"
|
||||
r = requests.post(url=url, headers=headers, data=json.dumps(data))
|
||||
|
||||
# 打印预测结果
|
||||
print(r.json()["results"])
|
||||
```
|
||||
|
||||
你可能需要根据实际情况修改```url```字符串中的端口号和服务模块名称。
|
||||
|
||||
上面所示代码都已写入测试脚本，可直接运行命令：```python tools/test_hubserving.py```
|
||||
|
||||
## 自定义修改服务模块
|
||||
如果需要修改服务逻辑，你一般需要操作以下步骤：
|
||||
|
||||
1、 停止服务
|
||||
```hub serving stop -m ocr_system```
|
||||
|
||||
2、 到相应的module.py文件中根据实际需求修改代码
|
||||
|
||||
3、 卸载旧服务包
|
||||
```hub uninstall ocr_system```
|
||||
|
||||
4、 安装修改后的新服务包
|
||||
```hub install deploy/hubserving/ocr_system/```
|
||||
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
|
||||
def read_params():
|
||||
cfg = Config()
|
||||
|
||||
#params for text detector
|
||||
cfg.det_algorithm = "DB"
|
||||
# cfg.det_model_dir = "./inference/ch_det_mv3_db/"
|
||||
cfg.det_model_dir = "./inference/det/"
|
||||
cfg.det_max_side_len = 960
|
||||
|
||||
#DB parmas
|
||||
cfg.det_db_thresh =0.3
|
||||
cfg.det_db_box_thresh =0.5
|
||||
cfg.det_db_unclip_ratio =2.0
|
||||
|
||||
# #EAST parmas
|
||||
# cfg.det_east_score_thresh = 0.8
|
||||
# cfg.det_east_cover_thresh = 0.1
|
||||
# cfg.det_east_nms_thresh = 0.2
|
||||
|
||||
# #params for text recognizer
|
||||
# cfg.rec_algorithm = "CRNN"
|
||||
# # cfg.rec_model_dir = "./inference/ch_det_mv3_crnn/"
|
||||
# cfg.rec_model_dir = "./inference/rec/"
|
||||
|
||||
# cfg.rec_image_shape = "3, 32, 320"
|
||||
# cfg.rec_char_type = 'ch'
|
||||
# cfg.rec_batch_num = 30
|
||||
# cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
|
||||
# cfg.use_space_char = True
|
||||
|
||||
return cfg
|
||||
|
|
@ -3,12 +3,14 @@
|
|||
"ocr_det": {
|
||||
"init_args": {
|
||||
"version": "1.0.0",
|
||||
"det_model_dir": "./inference/ch_det_mv3_db/",
|
||||
"use_gpu": true
|
||||
},
|
||||
"predict_args": {
|
||||
"visualization": false
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"port": 8866,
|
||||
"use_multiprocess": false,
|
||||
"workers": 2
|
||||
}
|
||||
|
|
@ -22,8 +22,6 @@ import paddlehub as hub
|
|||
from tools.infer.utility import draw_boxes, base64_to_cv2
|
||||
from tools.infer.predict_det import TextDetector
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
@moduleinfo(
|
||||
name="ocr_det",
|
||||
|
|
@ -33,43 +31,28 @@ class Config(object):
|
|||
author_email="paddle-dev@baidu.com",
|
||||
type="cv/text_recognition")
|
||||
class OCRDet(hub.Module):
|
||||
def _initialize(self,
|
||||
det_model_dir="",
|
||||
det_algorithm="DB",
|
||||
use_gpu=False
|
||||
):
|
||||
def _initialize(self, use_gpu=False):
|
||||
"""
|
||||
initialize with the necessary elements
|
||||
"""
|
||||
self.config = Config()
|
||||
self.config.use_gpu = use_gpu
|
||||
from ocr_det.params import read_params
|
||||
cfg = read_params()
|
||||
|
||||
cfg.use_gpu = use_gpu
|
||||
if use_gpu:
|
||||
try:
|
||||
_places = os.environ["CUDA_VISIBLE_DEVICES"]
|
||||
int(_places[0])
|
||||
print("use gpu: ", use_gpu)
|
||||
print("CUDA_VISIBLE_DEVICES: ", _places)
|
||||
cfg.gpu_mem = 8000
|
||||
except:
|
||||
raise RuntimeError(
|
||||
"Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
|
||||
)
|
||||
self.config.ir_optim = True
|
||||
self.config.gpu_mem = 8000
|
||||
cfg.ir_optim = True
|
||||
|
||||
#params for text detector
|
||||
self.config.det_algorithm = det_algorithm
|
||||
self.config.det_model_dir = det_model_dir
|
||||
# self.config.det_model_dir = "./inference/det/"
|
||||
|
||||
#DB parmas
|
||||
self.config.det_db_thresh =0.3
|
||||
self.config.det_db_box_thresh =0.5
|
||||
self.config.det_db_unclip_ratio =2.0
|
||||
|
||||
#EAST parmas
|
||||
self.config.det_east_score_thresh = 0.8
|
||||
self.config.det_east_cover_thresh = 0.1
|
||||
self.config.det_east_nms_thresh = 0.2
|
||||
self.text_detector = TextDetector(cfg)
|
||||
|
||||
def read_images(self, paths=[]):
|
||||
images = []
|
||||
|
|
@ -83,10 +66,9 @@ class OCRDet(hub.Module):
|
|||
images.append(img)
|
||||
return images
|
||||
|
||||
def det_text(self,
|
||||
def predict(self,
|
||||
images=[],
|
||||
paths=[],
|
||||
det_max_side_len=960,
|
||||
draw_img_save='ocr_det_result',
|
||||
visualization=False):
|
||||
"""
|
||||
|
|
@ -94,10 +76,8 @@ class OCRDet(hub.Module):
|
|||
Args:
|
||||
images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
|
||||
paths (list[str]): The paths of images. If paths not images
|
||||
use_gpu (bool): Whether to use gpu. Default false.
|
||||
output_dir (str): The directory to store output images.
|
||||
draw_img_save (str): The directory to store output images.
|
||||
visualization (bool): Whether to save image or not.
|
||||
box_thresh(float): the threshold of the detected text box's confidence
|
||||
Returns:
|
||||
res (list): The result of text detection box and save path of images.
|
||||
"""
|
||||
|
|
@ -111,8 +91,6 @@ class OCRDet(hub.Module):
|
|||
|
||||
assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
|
||||
|
||||
self.config.det_max_side_len = det_max_side_len
|
||||
text_detector = TextDetector(self.config)
|
||||
all_results = []
|
||||
for img in predicted_data:
|
||||
result = {'save_path': ''}
|
||||
|
|
@ -121,7 +99,7 @@ class OCRDet(hub.Module):
|
|||
result['data'] = []
|
||||
all_results.append(result)
|
||||
continue
|
||||
dt_boxes, elapse = text_detector(img)
|
||||
dt_boxes, elapse = self.text_detector(img)
|
||||
print("Predict time : ", elapse)
|
||||
result['data'] = dt_boxes.astype(np.int).tolist()
|
||||
|
||||
|
|
@ -146,7 +124,7 @@ class OCRDet(hub.Module):
|
|||
Run as a service.
|
||||
"""
|
||||
images_decode = [base64_to_cv2(image) for image in images]
|
||||
results = self.det_text(images_decode, **kwargs)
|
||||
results = self.predict(images_decode, **kwargs)
|
||||
return results
|
||||
|
||||
|
||||
|
|
@ -156,5 +134,5 @@ if __name__ == '__main__':
|
|||
'./doc/imgs/11.jpg',
|
||||
'./doc/imgs/12.jpg',
|
||||
]
|
||||
res = ocr.det_text(paths=image_path, visualization=True)
|
||||
res = ocr.predict(paths=image_path, visualization=True)
|
||||
print(res)
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
|
||||
def read_params():
|
||||
cfg = Config()
|
||||
|
||||
#params for text detector
|
||||
cfg.det_algorithm = "DB"
|
||||
cfg.det_model_dir = "./inference/ch_det_mv3_db/"
|
||||
cfg.det_max_side_len = 960
|
||||
|
||||
#DB parmas
|
||||
cfg.det_db_thresh =0.3
|
||||
cfg.det_db_box_thresh =0.5
|
||||
cfg.det_db_unclip_ratio =2.0
|
||||
|
||||
# #EAST parmas
|
||||
# cfg.det_east_score_thresh = 0.8
|
||||
# cfg.det_east_cover_thresh = 0.1
|
||||
# cfg.det_east_nms_thresh = 0.2
|
||||
|
||||
# #params for text recognizer
|
||||
# cfg.rec_algorithm = "CRNN"
|
||||
# cfg.rec_model_dir = "./inference/ch_det_mv3_crnn/"
|
||||
|
||||
# cfg.rec_image_shape = "3, 32, 320"
|
||||
# cfg.rec_char_type = 'ch'
|
||||
# cfg.rec_batch_num = 30
|
||||
# cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
|
||||
# cfg.use_space_char = True
|
||||
|
||||
return cfg
|
||||
|
|
@ -3,11 +3,13 @@
|
|||
"ocr_rec": {
|
||||
"init_args": {
|
||||
"version": "1.0.0",
|
||||
"det_model_dir": "./inference/ch_rec_mv3_crnn/",
|
||||
"use_gpu": true
|
||||
},
|
||||
"predict_args": {
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"port": 8867,
|
||||
"use_multiprocess": false,
|
||||
"workers": 2
|
||||
}
|
||||
|
|
@ -22,8 +22,6 @@ import paddlehub as hub
|
|||
from tools.infer.utility import base64_to_cv2
|
||||
from tools.infer.predict_rec import TextRecognizer
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
@moduleinfo(
|
||||
name="ocr_rec",
|
||||
|
|
@ -33,41 +31,28 @@ class Config(object):
|
|||
author_email="paddle-dev@baidu.com",
|
||||
type="cv/text_recognition")
|
||||
class OCRRec(hub.Module):
|
||||
def _initialize(self,
|
||||
rec_model_dir="",
|
||||
rec_algorithm="CRNN",
|
||||
rec_char_dict_path="./ppocr/utils/ppocr_keys_v1.txt",
|
||||
rec_batch_num=30,
|
||||
use_gpu=False
|
||||
):
|
||||
def _initialize(self, use_gpu=False):
|
||||
"""
|
||||
initialize with the necessary elements
|
||||
"""
|
||||
self.config = Config()
|
||||
self.config.use_gpu = use_gpu
|
||||
from ocr_rec.params import read_params
|
||||
cfg = read_params()
|
||||
|
||||
cfg.use_gpu = use_gpu
|
||||
if use_gpu:
|
||||
try:
|
||||
_places = os.environ["CUDA_VISIBLE_DEVICES"]
|
||||
int(_places[0])
|
||||
print("use gpu: ", use_gpu)
|
||||
print("CUDA_VISIBLE_DEVICES: ", _places)
|
||||
cfg.gpu_mem = 8000
|
||||
except:
|
||||
raise RuntimeError(
|
||||
"Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
|
||||
)
|
||||
self.config.ir_optim = True
|
||||
self.config.gpu_mem = 8000
|
||||
cfg.ir_optim = True
|
||||
|
||||
#params for text recognizer
|
||||
self.config.rec_algorithm = rec_algorithm
|
||||
self.config.rec_model_dir = rec_model_dir
|
||||
# self.config.rec_model_dir = "./inference/rec/"
|
||||
|
||||
self.config.rec_image_shape = "3, 32, 320"
|
||||
self.config.rec_char_type = 'ch'
|
||||
self.config.rec_batch_num = rec_batch_num
|
||||
self.config.rec_char_dict_path = rec_char_dict_path
|
||||
self.config.use_space_char = True
|
||||
self.text_recognizer = TextRecognizer(cfg)
|
||||
|
||||
def read_images(self, paths=[]):
|
||||
images = []
|
||||
|
|
@ -81,7 +66,7 @@ class OCRRec(hub.Module):
|
|||
images.append(img)
|
||||
return images
|
||||
|
||||
def rec_text(self,
|
||||
def predict(self,
|
||||
images=[],
|
||||
paths=[]):
|
||||
"""
|
||||
|
|
@ -102,14 +87,13 @@ class OCRRec(hub.Module):
|
|||
|
||||
assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
|
||||
|
||||
text_recognizer = TextRecognizer(self.config)
|
||||
img_list = []
|
||||
for img in predicted_data:
|
||||
if img is None:
|
||||
continue
|
||||
img_list.append(img)
|
||||
try:
|
||||
rec_res, predict_time = text_recognizer(img_list)
|
||||
rec_res, predict_time = self.text_recognizer(img_list)
|
||||
except Exception as e:
|
||||
print(e)
|
||||
return []
|
||||
|
|
@ -121,7 +105,7 @@ class OCRRec(hub.Module):
|
|||
Run as a service.
|
||||
"""
|
||||
images_decode = [base64_to_cv2(image) for image in images]
|
||||
results = self.det_text(images_decode, **kwargs)
|
||||
results = self.predict(images_decode, **kwargs)
|
||||
return results
|
||||
|
||||
|
||||
|
|
@ -132,5 +116,5 @@ if __name__ == '__main__':
|
|||
'./doc/imgs_words/ch/word_2.jpg',
|
||||
'./doc/imgs_words/ch/word_3.jpg',
|
||||
]
|
||||
res = ocr.rec_text(paths=image_path)
|
||||
res = ocr.predict(paths=image_path)
|
||||
print(res)
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
|
||||
def read_params():
|
||||
cfg = Config()
|
||||
|
||||
# #params for text detector
|
||||
# cfg.det_algorithm = "DB"
|
||||
# cfg.det_model_dir = "./inference/ch_det_mv3_db/"
|
||||
# cfg.det_max_side_len = 960
|
||||
|
||||
# #DB parmas
|
||||
# cfg.det_db_thresh =0.3
|
||||
# cfg.det_db_box_thresh =0.5
|
||||
# cfg.det_db_unclip_ratio =2.0
|
||||
|
||||
# #EAST parmas
|
||||
# cfg.det_east_score_thresh = 0.8
|
||||
# cfg.det_east_cover_thresh = 0.1
|
||||
# cfg.det_east_nms_thresh = 0.2
|
||||
|
||||
#params for text recognizer
|
||||
cfg.rec_algorithm = "CRNN"
|
||||
cfg.rec_model_dir = "./inference/ch_rec_mv3_crnn/"
|
||||
|
||||
cfg.rec_image_shape = "3, 32, 320"
|
||||
cfg.rec_char_type = 'ch'
|
||||
cfg.rec_batch_num = 30
|
||||
cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
|
||||
cfg.use_space_char = True
|
||||
|
||||
return cfg
|
||||
|
|
@ -3,14 +3,15 @@
|
|||
"ocr_system": {
|
||||
"init_args": {
|
||||
"version": "1.0.0",
|
||||
"det_model_dir": "./inference/ch_det_mv3_db/",
|
||||
"rec_model_dir": "./inference/ch_rec_mv3_crnn/",
|
||||
"use_gpu": true
|
||||
},
|
||||
"predict_args": {
|
||||
"visualization": false
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"port": 8868,
|
||||
"use_multiprocess": false,
|
||||
"workers": 2
|
||||
}
|
||||
|
||||
|
|
@ -23,9 +23,6 @@ from tools.infer.utility import draw_ocr, base64_to_cv2
|
|||
from tools.infer.predict_system import TextSystem
|
||||
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
@moduleinfo(
|
||||
name="ocr_system",
|
||||
version="1.0.0",
|
||||
|
|
@ -34,58 +31,28 @@ class Config(object):
|
|||
author_email="paddle-dev@baidu.com",
|
||||
type="cv/text_recognition")
|
||||
class OCRSystem(hub.Module):
|
||||
def _initialize(self,
|
||||
det_model_dir="",
|
||||
det_algorithm="DB",
|
||||
rec_model_dir="",
|
||||
rec_algorithm="CRNN",
|
||||
rec_char_dict_path="./ppocr/utils/ppocr_keys_v1.txt",
|
||||
rec_batch_num=30,
|
||||
use_gpu=False
|
||||
):
|
||||
def _initialize(self, use_gpu=False):
|
||||
"""
|
||||
initialize with the necessary elements
|
||||
"""
|
||||
self.config = Config()
|
||||
self.config.use_gpu = use_gpu
|
||||
from ocr_system.params import read_params
|
||||
cfg = read_params()
|
||||
|
||||
cfg.use_gpu = use_gpu
|
||||
if use_gpu:
|
||||
try:
|
||||
_places = os.environ["CUDA_VISIBLE_DEVICES"]
|
||||
int(_places[0])
|
||||
print("use gpu: ", use_gpu)
|
||||
print("CUDA_VISIBLE_DEVICES: ", _places)
|
||||
cfg.gpu_mem = 8000
|
||||
except:
|
||||
raise RuntimeError(
|
||||
"Environment Variable CUDA_VISIBLE_DEVICES is not set correctly. If you wanna use gpu, please set CUDA_VISIBLE_DEVICES via export CUDA_VISIBLE_DEVICES=cuda_device_id."
|
||||
)
|
||||
self.config.ir_optim = True
|
||||
self.config.gpu_mem = 8000
|
||||
cfg.ir_optim = True
|
||||
|
||||
#params for text detector
|
||||
self.config.det_algorithm = det_algorithm
|
||||
self.config.det_model_dir = det_model_dir
|
||||
# self.config.det_model_dir = "./inference/det/"
|
||||
|
||||
#DB parmas
|
||||
self.config.det_db_thresh =0.3
|
||||
self.config.det_db_box_thresh =0.5
|
||||
self.config.det_db_unclip_ratio =2.0
|
||||
|
||||
#EAST parmas
|
||||
self.config.det_east_score_thresh = 0.8
|
||||
self.config.det_east_cover_thresh = 0.1
|
||||
self.config.det_east_nms_thresh = 0.2
|
||||
|
||||
#params for text recognizer
|
||||
self.config.rec_algorithm = rec_algorithm
|
||||
self.config.rec_model_dir = rec_model_dir
|
||||
# self.config.rec_model_dir = "./inference/rec/"
|
||||
|
||||
self.config.rec_image_shape = "3, 32, 320"
|
||||
self.config.rec_char_type = 'ch'
|
||||
self.config.rec_batch_num = rec_batch_num
|
||||
self.config.rec_char_dict_path = rec_char_dict_path
|
||||
self.config.use_space_char = True
|
||||
self.text_sys = TextSystem(cfg)
|
||||
|
||||
def read_images(self, paths=[]):
|
||||
images = []
|
||||
|
|
@ -99,10 +66,9 @@ class OCRSystem(hub.Module):
|
|||
images.append(img)
|
||||
return images
|
||||
|
||||
def recognize_text(self,
|
||||
def predict(self,
|
||||
images=[],
|
||||
paths=[],
|
||||
det_max_side_len=960,
|
||||
draw_img_save='ocr_result',
|
||||
visualization=False,
|
||||
text_thresh=0.5):
|
||||
|
|
@ -111,11 +77,8 @@ class OCRSystem(hub.Module):
|
|||
Args:
|
||||
images (list(numpy.ndarray)): images data, shape of each is [H, W, C]. If images not paths
|
||||
paths (list[str]): The paths of images. If paths not images
|
||||
use_gpu (bool): Whether to use gpu.
|
||||
batch_size(int): the program deals once with one
|
||||
output_dir (str): The directory to store output images.
|
||||
draw_img_save (str): The directory to store output images.
|
||||
visualization (bool): Whether to save image or not.
|
||||
box_thresh(float): the threshold of the detected text box's confidence
|
||||
text_thresh(float): the threshold of the recognize chinese texts' confidence
|
||||
Returns:
|
||||
res (list): The result of chinese texts and save path of images.
|
||||
|
|
@ -130,8 +93,6 @@ class OCRSystem(hub.Module):
|
|||
|
||||
assert predicted_data != [], "There is not any image to be predicted. Please check the input data."
|
||||
|
||||
self.config.det_max_side_len = det_max_side_len
|
||||
text_sys = TextSystem(self.config)
|
||||
cnt = 0
|
||||
all_results = []
|
||||
for img in predicted_data:
|
||||
|
|
@ -142,7 +103,7 @@ class OCRSystem(hub.Module):
|
|||
all_results.append(result)
|
||||
continue
|
||||
starttime = time.time()
|
||||
dt_boxes, rec_res = text_sys(img)
|
||||
dt_boxes, rec_res = self.text_sys(img)
|
||||
elapse = time.time() - starttime
|
||||
cnt += 1
|
||||
print("Predict time of image %d: %.3fs" % (cnt, elapse))
|
||||
|
|
@ -187,7 +148,7 @@ class OCRSystem(hub.Module):
|
|||
Run as a service.
|
||||
"""
|
||||
images_decode = [base64_to_cv2(image) for image in images]
|
||||
results = self.recognize_text(images_decode, **kwargs)
|
||||
results = self.predict(images_decode, **kwargs)
|
||||
return results
|
||||
|
||||
|
||||
|
|
@ -197,5 +158,5 @@ if __name__ == '__main__':
|
|||
'./doc/imgs/11.jpg',
|
||||
'./doc/imgs/12.jpg',
|
||||
]
|
||||
res = ocr.recognize_text(paths=image_path, visualization=True)
|
||||
res = ocr.predict(paths=image_path, visualization=False)
|
||||
print(res)
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
# -*- coding:utf-8 -*-
|
||||
from __future__ import absolute_import
|
||||
from __future__ import division
|
||||
from __future__ import print_function
|
||||
|
||||
|
||||
class Config(object):
|
||||
pass
|
||||
|
||||
|
||||
def read_params():
|
||||
cfg = Config()
|
||||
|
||||
#params for text detector
|
||||
cfg.det_algorithm = "DB"
|
||||
cfg.det_model_dir = "./inference/ch_det_mv3_db/"
|
||||
cfg.det_max_side_len = 960
|
||||
|
||||
#DB parmas
|
||||
cfg.det_db_thresh =0.3
|
||||
cfg.det_db_box_thresh =0.5
|
||||
cfg.det_db_unclip_ratio =2.0
|
||||
|
||||
#EAST parmas
|
||||
cfg.det_east_score_thresh = 0.8
|
||||
cfg.det_east_cover_thresh = 0.1
|
||||
cfg.det_east_nms_thresh = 0.2
|
||||
|
||||
#params for text recognizer
|
||||
cfg.rec_algorithm = "CRNN"
|
||||
cfg.rec_model_dir = "./inference/ch_rec_mv3_crnn/"
|
||||
|
||||
cfg.rec_image_shape = "3, 32, 320"
|
||||
cfg.rec_char_type = 'ch'
|
||||
cfg.rec_batch_num = 30
|
||||
cfg.rec_char_dict_path = "./ppocr/utils/ppocr_keys_v1.txt"
|
||||
cfg.use_space_char = True
|
||||
|
||||
return cfg
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
# 服务部署
|
||||
|
||||
PaddleOCR提供2种服务部署方式：
|
||||
- 基于HubServing的部署：已集成到PaddleOCR中（[code](https://github.com/PaddlePaddle/PaddleOCR/tree/develop/deploy/ocr_hubserving)），按照本教程使用；
|
||||
- 基于HubServing的部署：已集成到PaddleOCR中（[code](https://github.com/PaddlePaddle/PaddleOCR/tree/develop/deploy/hubserving)），按照本教程使用；
|
||||
- 基于PaddleServing的部署：详见PaddleServing官网[demo](https://github.com/PaddlePaddle/Serving/tree/develop/python/examples/ocr)，后续也将集成到PaddleOCR。
|
||||
|
||||
服务部署目录下包括检测、识别、2阶段串联三种服务包，根据需求选择相应的服务包进行安装和启动。目录如下：
|
||||
|
|
@ -15,12 +15,13 @@ deploy/hubserving/
|
|||
每个服务包下包含3个文件。以2阶段串联服务包为例，目录如下：
|
||||
```
|
||||
deploy/hubserving/ocr_system/
|
||||
└─ __init__.py 空文件
|
||||
└─ config.json 配置文件，启动服务时作为参数传入
|
||||
└─ module.py 主模块，包含服务的完整逻辑
|
||||
└─ __init__.py 空文件，必选
|
||||
└─ config.json 配置文件，可选，使用配置启动服务时作为参数传入
|
||||
└─ module.py 主模块，必选，包含服务的完整逻辑
|
||||
└─ params.py 参数文件，必选，包含模型路径、前后处理参数等参数
|
||||
```
|
||||
|
||||
## 启动服务
|
||||
## 快速启动服务
|
||||
以下步骤以检测+识别2阶段串联服务为例，如果只需要检测服务或识别服务，替换相应文件路径即可。
|
||||
### 1. 安装paddlehub
|
||||
```pip3 install paddlehub --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple```
|
||||
|
|
@ -31,39 +32,71 @@ PaddleOCR提供3种服务模块，根据需要安装所需模块。如：
|
|||
安装检测服务模块：
|
||||
```hub install deploy/hubserving/ocr_det/```
|
||||
|
||||
或，安装识别服务模块：
|
||||
或，安装识别服务模块：
|
||||
```hub install deploy/hubserving/ocr_rec/```
|
||||
|
||||
或，安装检测+识别串联服务模块：
|
||||
```hub install deploy/hubserving/ocr_system/```
|
||||
|
||||
### 3. 修改配置文件
|
||||
在config.json中指定模型路径、是否使用GPU、是否对结果做可视化等参数，如，串联服务ocr_system的配置：
|
||||
### 3. 启动服务
|
||||
#### 方式1. 命令行命令启动（仅支持CPU）
|
||||
**启动命令：**
|
||||
```shell
|
||||
$ hub serving start --modules [Module1==Version1, Module2==Version2, ...] \
|
||||
--port XXXX \
|
||||
--use_multiprocess \
|
||||
--workers \
|
||||
```
|
||||
|
||||
**参数：**
|
||||
|
||||
|参数|用途|
|
||||
|-|-|
|
||||
|--modules/-m|PaddleHub Serving预安装模型，以多个Module==Version键值对的形式列出<br>*`当不指定Version时，默认选择最新版本`*|
|
||||
|--port/-p|服务端口，默认为8866|
|
||||
|--use_multiprocess|是否启用并发方式，默认为单进程方式，推荐多核CPU机器使用此方式<br>*`Windows操作系统只支持单进程方式`*|
|
||||
|--workers|在并发方式下指定的并发任务数，默认为`2*cpu_count-1`，其中`cpu_count`为CPU核数|
|
||||
|
||||
如启动串联服务： ```hub serving start -m ocr_system```
|
||||
|
||||
这样就完成了一个服务化API的部署，使用默认端口号8866。
|
||||
|
||||
#### 方式2. 配置文件启动（支持CPU、GPU）
|
||||
**启动命令：**
|
||||
```hub serving start --config/-c config.json```
|
||||
|
||||
其中，`config.json`格式如下：
|
||||
```python
|
||||
{
|
||||
"modules_info": {
|
||||
"ocr_system": {
|
||||
"init_args": {
|
||||
"version": "1.0.0",
|
||||
"det_model_dir": "./inference/det/",
|
||||
"rec_model_dir": "./inference/rec/",
|
||||
"use_gpu": true
|
||||
},
|
||||
"predict_args": {
|
||||
"visualization": false
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"port": 8868,
|
||||
"use_multiprocess": false,
|
||||
"workers": 2
|
||||
}
|
||||
```
|
||||
其中，模型路径对应的模型为```inference模型```。
|
||||
|
||||
### 4. 运行启动命令
|
||||
```hub serving start -m ocr_system --config hubserving/ocr_det/config.json```
|
||||
- `init_args`中的可配参数与`module.py`中的`_initialize`函数接口一致。其中，**当`use_gpu`为`true`时，表示使用GPU启动服务**。
|
||||
- `predict_args`中的可配参数与`module.py`中的`predict`函数接口一致。
|
||||
|
||||
这样就完成了一个服务化API的部署，默认端口号为8866。
|
||||
**注意:**
|
||||
- 使用配置文件启动服务时，其他参数会被忽略。
|
||||
- 如果使用GPU预测(即，`use_gpu`置为`true`)，则需要在启动服务之前，设置CUDA_VISIBLE_DEVICES环境变量，如：```export CUDA_VISIBLE_DEVICES=0```，否则不用设置。
|
||||
|
||||
**NOTE:** 如使用GPU预测(即，config中use_gpu置为true)，则需要在启动服务之前，设置CUDA_VISIBLE_DEVICES环境变量，如：```export CUDA_VISIBLE_DEVICES=0```，否则不用设置。
|
||||
如，使用GPU 3号卡启动串联服务：
|
||||
```shell
|
||||
export CUDA_VISIBLE_DEVICES=3
|
||||
hub serving start -c deploy/hubserving/ocr_system/config.json
|
||||
```
|
||||
|
||||
## 发送预测请求
|
||||
配置好服务端，以下数行代码即可实现发送预测请求，获取预测结果:
|
||||
|
|
@ -89,21 +122,25 @@ r = requests.post(url=url, headers=headers, data=json.dumps(data))
|
|||
print(r.json()["results"])
|
||||
```
|
||||
|
||||
你可能需要根据实际情况修改```url```字符串中的端口号和服务模块名称。
|
||||
你可能需要根据实际情况修改`url`字符串中的端口号和服务模块名称。
|
||||
|
||||
上面所示代码都已写入测试脚本，可直接运行命令：```python tools/test_hubserving.py```
|
||||
|
||||
## 自定义修改服务模块
|
||||
如果需要修改服务逻辑，你一般需要操作以下步骤：
|
||||
如果需要修改服务逻辑，你一般需要操作以下步骤（以修改`ocr_system`为例）：
|
||||
|
||||
1、 停止服务
|
||||
```hub serving stop -m ocr_system```
|
||||
- 1、 停止服务
|
||||
```hub serving stop --port/-p XXXX```
|
||||
|
||||
2、 到相应的module.py文件中根据实际需求修改代码
|
||||
- 2、 到相应的`module.py`和`params.py`等文件中根据实际需求修改代码。
|
||||
例如，如果需要替换部署服务所用模型，则需要到`params.py`中修改模型路径参数`det_model_dir`和`rec_model_dir`，当然，同时可能还需要修改其他相关参数，请根据实际情况修改调试。 建议修改后先直接运行`module.py`调试，能正确运行预测后再启动服务测试。
|
||||
|
||||
3、 卸载旧服务包
|
||||
- 3、 卸载旧服务包
|
||||
```hub uninstall ocr_system```
|
||||
|
||||
4、 安装修改后的新服务包
|
||||
- 4、 安装修改后的新服务包
|
||||
```hub install deploy/hubserving/ocr_system/```
|
||||
|
||||
- 5、重新启动服务
|
||||
```hub serving start -m ocr_system```
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue