From fc85051d6472469d1a301b43aafcb767da7258f4 Mon Sep 17 00:00:00 2001 From: littletomatodonkey <2120160898@bit.edu.cn> Date: Thu, 17 Dec 2020 15:28:19 +0800 Subject: [PATCH] add support for cpu infer (#1480) * add support for cpu infer * fix readme --- StyleText/README.md | 11 ++++++----- StyleText/README_ch.md | 5 +++-- StyleText/engine/predictors.py | 1 + StyleText/tools/synth_dataset.py | 8 ++++++++ StyleText/tools/synth_image.py | 6 +++--- 5 files changed, 21 insertions(+), 10 deletions(-) diff --git a/StyleText/README.md b/StyleText/README.md index 648b12674..632f7b6da 100644 --- a/StyleText/README.md +++ b/StyleText/README.md @@ -69,12 +69,13 @@ 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`. @@ -122,7 +123,7 @@ In actual application scenarios, it is often necessary to synthesize pictures in * `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings（'\n'）. Corpus generator samples one line each time. -Example of corpus file: +Example of corpus file: ``` PaddleOCR 飞桨文字识别 @@ -139,9 +140,9 @@ 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.
diff --git a/StyleText/README_ch.md b/StyleText/README_ch.md index 0dd5822b1..5b8a3ee0f 100644 --- a/StyleText/README_ch.md +++ b/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。
diff --git a/StyleText/engine/predictors.py b/StyleText/engine/predictors.py index d9f4afe4a..a1ba21f1b 100644 --- a/StyleText/engine/predictors.py +++ b/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"] diff --git a/StyleText/tools/synth_dataset.py b/StyleText/tools/synth_dataset.py index 4a0e6d5e1..a75f7f393 100644 --- a/StyleText/tools/synth_dataset.py +++ b/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 diff --git a/StyleText/tools/synth_image.py b/StyleText/tools/synth_image.py index 7b4827b82..cbc311867 100644 --- a/StyleText/tools/synth_image.py +++ b/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()