提交 78d3349e 编写于 作者: W weishengyu

add notice in size of style images

上级 39f14763
...@@ -72,7 +72,10 @@ fusion_generator: ...@@ -72,7 +72,10 @@ fusion_generator:
python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
``` ```
* Note: 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.
So the height of style images should be around 32 pixels. Images in other sizes may behave poorly.
For example, enter the following image and corpus `PaddleOCR`. For example, enter the following image and corpus `PaddleOCR`.
......
...@@ -63,7 +63,10 @@ fusion_generator: ...@@ -63,7 +63,10 @@ fusion_generator:
```python ```python
python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
``` ```
* 注意: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。
如果输入图像尺寸相差过多,效果可能不佳。
例如,输入如下图片和语料"PaddleOCR": 例如,输入如下图片和语料"PaddleOCR":
......
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