未验证 提交 fc85051d 编写于 作者: L littletomatodonkey 提交者: GitHub

add support for cpu infer (#1480)

* add support for cpu infer

* fix readme
上级 84b4323a
...@@ -69,12 +69,13 @@ fusion_generator: ...@@ -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. 1. You can run `tools/synth_image` and generate the demo image, which is saved in the current folder.
```python ```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 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. 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`. 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 ...@@ -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. * `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 PaddleOCR
飞桨文字识别 飞桨文字识别
...@@ -139,9 +140,9 @@ We provide a general dataset containing Chinese, English and Korean (50,000 imag ...@@ -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: 2. You can run the following command to start synthesis task:
``` bash ``` 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"> <div align="center">
<img src="examples/style_images/1.jpg" width="300"> <img src="examples/style_images/1.jpg" width="300">
<img src="examples/style_images/2.jpg" width="300"> <img src="examples/style_images/2.jpg" width="300">
......
...@@ -61,11 +61,12 @@ fusion_generator: ...@@ -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: 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 ```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。 * 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。 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": 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_ ...@@ -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: 2. 运行`tools/synth_dataset`合成数据:
``` bash ``` 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。 我们在examples目录下提供了样例图片和语料。
<div align="center"> <div align="center">
......
...@@ -28,6 +28,7 @@ class StyleTextRecPredictor(object): ...@@ -28,6 +28,7 @@ class StyleTextRecPredictor(object):
], "Generator {} not supported.".format(algorithm) ], "Generator {} not supported.".format(algorithm)
use_gpu = config["Global"]['use_gpu'] use_gpu = config["Global"]['use_gpu']
check_gpu(use_gpu) check_gpu(use_gpu)
paddle.set_device('gpu' if use_gpu else 'cpu')
self.logger = get_logger() self.logger = get_logger()
self.generator = getattr(style_text_rec, algorithm)(config) self.generator = getattr(style_text_rec, algorithm)(config)
self.height = config["Global"]["image_height"] self.height = config["Global"]["image_height"]
......
...@@ -11,6 +11,14 @@ ...@@ -11,6 +11,14 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and # See the License for the specific language governing permissions and
# limitations under the License. # 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 from engine.synthesisers import DatasetSynthesiser
......
...@@ -16,13 +16,13 @@ import cv2 ...@@ -16,13 +16,13 @@ import cv2
import sys import sys
import glob import glob
from utils.config import ArgsParser
from engine.synthesisers import ImageSynthesiser
__dir__ = os.path.dirname(os.path.abspath(__file__)) __dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__) sys.path.append(__dir__)
sys.path.append(os.path.abspath(os.path.join(__dir__, '..'))) sys.path.append(os.path.abspath(os.path.join(__dir__, '..')))
from utils.config import ArgsParser
from engine.synthesisers import ImageSynthesiser
def synth_image(): def synth_image():
args = ArgsParser().parse_args() args = ArgsParser().parse_args()
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册