Replies: 12 comments
-
使用的什么GPU呢 |
Beta Was this translation helpful? Give feedback.
-
cpu模型,转onnx也是慢 |
Beta Was this translation helpful? Give feedback.
-
建议使用GPU哈,本来ch_PP-OCRv4_rec_hgnet这个模型就比较大,使用CPU会更慢的 |
Beta Was this translation helpful? Give feedback.
-
发现个问题。 |
Beta Was this translation helpful? Give feedback.
-
另外,这里说图片经过二值化转换后,再转换为ndarray数组,识别,准确率会高? |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
resize放大两倍,有时准确率会提升,有时会降低,怎么处理resize比较好? |
Beta Was this translation helpful? Give feedback.
-
针对不同的场景是会有不同的表现的哈,不建议放大resize,会增加模型的推理时间的哈 |
Beta Was this translation helpful? Give feedback.
-
另外,对于这个问题是在同一张图片上进行测试的吗,如果是同一张图片能否提供一下图片我们这边需要测试下哈 |
Beta Was this translation helpful? Give feedback.
-
测试图片如下。另外有什么好的padding方法吗? |
Beta Was this translation helpful? Give feedback.
-
ocr = PaddleOCR(
ocr = PaddleOCR( |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
请尽量不要包含图片在问题中/Please try to not include the image in the issue.
.
ch_PP-OCRv4_rec_hgnet.yml 用这个模型转换成onnx进行识别,速度超级慢,怎么加速?
Beta Was this translation helpful? Give feedback.
All reactions