Merge branch 'dygraph' into dy3

StyleText/README.md

@@ -69,12 +69,14 @@ fusion_generator:
 1. You can run `tools/synth_image` and generate the demo image, which is saved in the current folder.
 
 ```python
-python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
+python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
 ```
 
 * Note 1: The language options is correspond to the corpus. Currently, the tool only supports English, Simplified Chinese and Korean.
-* Note 2: Synth-Text is mainly used to generate images for OCR recognition models. 
+* Note 2: Synth-Text is mainly used to generate images for OCR recognition models.
   So the height of style images should be around 32 pixels. Images in other sizes may behave poorly.
+* Note 3: You can modify `use_gpu` in `configs/config.yml` to determine whether to use GPU for prediction.
+
 
 
 For example, enter the following image and corpus `PaddleOCR`.
@@ -139,9 +141,10 @@ We provide a general dataset containing Chinese, English and Korean (50,000 imag
 2. You can run the following command to start synthesis task:
 
    ``` bash
-   python -m tools.synth_dataset.py -c configs/dataset_config.yml
+   python3 tools/synth_dataset.py -c configs/dataset_config.yml
    ```
-We also provide example corpus and images in `examples` folder. 
+
+We also provide example corpus and images in `examples` folder.
     <div align="center">
         <img src="examples/style_images/1.jpg" width="300">
         <img src="examples/style_images/2.jpg" width="300">

StyleText/README_ch.md

@@ -61,11 +61,12 @@ fusion_generator:
 输入一张风格图和一段文字语料，运行tools/synth_image，合成单张图片，结果图像保存在当前目录下：
 
 ```python
-python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
+python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
 ```
 * 注1：语言选项和语料相对应，目前该工具只支持英文、简体中文和韩语。
 * 注2：Style-Text生成的数据主要应用于OCR识别场景。基于当前PaddleOCR识别模型的设计，我们主要支持高度在32左右的风格图像。
   如果输入图像尺寸相差过多，效果可能不佳。
+* 注3：可以通过修改配置文件中的`use_gpu`(true或者false)参数来决定是否使用GPU进行预测。
 
 
 例如，输入如下图片和语料"PaddleOCR":
@@ -127,7 +128,7 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
 2. 运行`tools/synth_dataset`合成数据：
 
    ``` bash
-   python -m tools.synth_dataset -c configs/dataset_config.yml
+   python tools/synth_dataset.py -c configs/dataset_config.yml
    ```
    我们在examples目录下提供了样例图片和语料。
     <div align="center">

StyleText/engine/predictors.py

@@ -28,6 +28,7 @@ class StyleTextRecPredictor(object):
                              ], "Generator {} not supported.".format(algorithm)
         use_gpu = config["Global"]['use_gpu']
         check_gpu(use_gpu)
+        paddle.set_device('gpu' if use_gpu else 'cpu')
         self.logger = get_logger()
         self.generator = getattr(style_text_rec, algorithm)(config)
         self.height = config["Global"]["image_height"]

StyleText/tools/synth_dataset.py

@@ -11,6 +11,14 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+
+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__, '..')))
+
 from engine.synthesisers import DatasetSynthesiser
 
 

StyleText/tools/synth_image.py

@@ -16,13 +16,13 @@ import cv2
 import sys
 import glob
 
-from utils.config import ArgsParser
-from engine.synthesisers import ImageSynthesiser
-
 __dir__ = os.path.dirname(os.path.abspath(__file__))
 sys.path.append(__dir__)
 sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
 
+from utils.config import ArgsParser
+from engine.synthesisers import ImageSynthesiser
+
 
 def synth_image():
     args = ArgsParser().parse_args()

deploy/cpp_infer/readme_en.md

@@ -107,10 +107,10 @@ make inference_lib_dist
 For more compilation parameter options, please refer to the official website of the Paddle C++ inference library:[https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html](https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html).
 
 
-* After the compilation process, you can see the following files in the folder of `build/fluid_inference_install_dir/`.
+* After the compilation process, you can see the following files in the folder of `build/paddle_inference_install_dir/`.
 
 ```
-build/fluid_inference_install_dir/
+build/paddle_inference_install_dir/
 |-- CMakeCache.txt
 |-- paddle
 |-- third_party

deploy/cpp_infer/src/preprocess_op.cpp

@@ -81,14 +81,14 @@ void ResizeImgType0::Run(const cv::Mat &img, cv::Mat &resize_img,
   else if (resize_h / 32 < 1 + 1e-5)
     resize_h = 32;
   else
-    resize_h = (resize_h / 32 - 1) * 32;
+    resize_h = (resize_h / 32) * 32;
 
   if (resize_w % 32 == 0)
     resize_w = resize_w;
   else if (resize_w / 32 < 1 + 1e-5)
     resize_w = 32;
   else
-    resize_w = (resize_w / 32 - 1) * 32;
+    resize_w = (resize_w / 32) * 32;
 
   cv::resize(img, resize_img, cv::Size(resize_w, resize_h));
 

deploy/cpp_infer/tools/config.txt

@@ -11,7 +11,7 @@ max_side_len  960
 det_db_thresh  0.3
 det_db_box_thresh  0.5
 det_db_unclip_ratio  2.0
-det_model_dir  ./inference/ch__ppocr_mobile_v2.0_det_infer/
+det_model_dir  ./inference/ch_ppocr_mobile_v2.0_det_infer/
 
 # cls config
 use_angle_cls 0

paddleocr.py

@@ -262,8 +262,8 @@ class PaddleOCR(predict_system.TextSystem):
             logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
             sys.exit(0)
 
-        postprocess_params.rec_char_dict_path = Path(
-            __file__).parent / postprocess_params.rec_char_dict_path
+        postprocess_params.rec_char_dict_path = str(
+            Path(__file__).parent / postprocess_params.rec_char_dict_path)
 
         # init det_model and rec_model
         super().__init__(postprocess_params)

setup.py

@@ -32,7 +32,7 @@ setup(
     package_dir={'paddleocr': ''},
     include_package_data=True,
     entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version='2.0.1',
+    version='2.0.2',
     install_requires=requirements,
     license='Apache License 2.0',
     description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',

tools/infer/predict_det.py

@@ -35,6 +35,7 @@ logger = get_logger()
 
 class TextDetector(object):
     def __init__(self, args):
+        self.args = args
         self.det_algorithm = args.det_algorithm
         self.use_zero_copy_run = args.use_zero_copy_run
         pre_process_list = [{
@@ -70,6 +71,9 @@ class TextDetector(object):
             postprocess_params["cover_thresh"] = args.det_east_cover_thresh
             postprocess_params["nms_thresh"] = args.det_east_nms_thresh
         elif self.det_algorithm == "SAST":
+            pre_process_list[0] = {
+                'DetResizeForTest': {'resize_long': args.det_limit_side_len}
+            }
             postprocess_params['name'] = 'SASTPostProcess'
             postprocess_params["score_thresh"] = args.det_sast_score_thresh
             postprocess_params["nms_thresh"] = args.det_sast_nms_thresh

tools/infer/utility.py

@@ -33,6 +33,8 @@ def parse_args():
     parser.add_argument("--use_gpu", type=str2bool, default=True)
     parser.add_argument("--ir_optim", type=str2bool, default=True)
     parser.add_argument("--use_tensorrt", type=str2bool, default=False)
+    parser.add_argument("--use_fp16", type=str2bool, default=False)
+    parser.add_argument("--max_batch_size", type=int, default=10)
     parser.add_argument("--gpu_mem", type=int, default=8000)
 
     # params for text detector
@@ -46,7 +48,7 @@ def parse_args():
     parser.add_argument("--det_db_thresh", type=float, default=0.3)
     parser.add_argument("--det_db_box_thresh", type=float, default=0.5)
     parser.add_argument("--det_db_unclip_ratio", type=float, default=1.6)
-
+    parser.add_argument("--max_batch_size", type=int, default=10)
     # EAST parmas
     parser.add_argument("--det_east_score_thresh", type=float, default=0.8)
     parser.add_argument("--det_east_cover_thresh", type=float, default=0.1)
@@ -62,7 +64,7 @@ def parse_args():
     parser.add_argument("--rec_model_dir", type=str)
     parser.add_argument("--rec_image_shape", type=str, default="3, 32, 320")
     parser.add_argument("--rec_char_type", type=str, default='ch')
-    parser.add_argument("--rec_batch_num", type=int, default=6)
+    parser.add_argument("--rec_batch_num", type=int, default=1)
     parser.add_argument("--max_text_length", type=int, default=25)
     parser.add_argument(
         "--rec_char_dict_path",
@@ -78,7 +80,7 @@ def parse_args():
     parser.add_argument("--cls_model_dir", type=str)
     parser.add_argument("--cls_image_shape", type=str, default="3, 48, 192")
     parser.add_argument("--label_list", type=list, default=['0', '180'])
-    parser.add_argument("--cls_batch_num", type=int, default=30)
+    parser.add_argument("--cls_batch_num", type=int, default=6)
     parser.add_argument("--cls_thresh", type=float, default=0.9)
 
     parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
@@ -113,6 +115,11 @@ def create_predictor(args, mode, logger):
 
     if args.use_gpu:
         config.enable_use_gpu(args.gpu_mem, 0)
+        if args.use_tensorrt:
+            config.enable_tensorrt_engine(
+                precision_mode=AnalysisConfig.Precision.Half
+                if args.use_fp16 else AnalysisConfig.Precision.Float32,
+                max_batch_size=args.max_batch_size)
     else:
         config.disable_gpu()
         config.set_cpu_math_library_num_threads(6)