PaddleSharp icon indicating copy to clipboard operation
PaddleSharp copied to clipboard

.NET/C# binding for Baidu paddle inference library and PaddleOCR

Results 70 PaddleSharp issues
Sort by recently updated
recently updated
newest added

### Feature request type sample request ### Is your feature request related to a problem? Please describe Sdcb.PaddleOCR.Models.Local不应该强制依赖V3和V4模型,这样生成的包要小点 ### Describe the solution you'd like Sdcb.PaddleOCR.Models.Local不应该强制依赖V3和V4模型,这样生成的包要小点 ### Describe alternatives you've considered...

### Feature request type sample request ### Is your feature request related to a problem? Please describe 请问本库是否支持加载自己用PaddleOCR训练的recognition模型? ### Describe the solution you'd like 请问是否有调用自己用PaddleOCR训练的recognition模型的示例? ### Describe alternatives you've considered...

### Describe the bug PaddleOCRAll.Run()对一批图片进行异步提取会报外部组件异常,它并不是一开始就报错的,可能是处理前面几张图片后开始报错,但是如果同步一张一张处理就不会报错,如何解决这个问题? ### Steps to reproduce the bug . ### Expected behavior _No response_ ### Screenshots _No response_ ### Release version _No response_ ### IDE _No response_...

### Feature request type sample request ### Is your feature request related to a problem? Please describe 您好,GPU不兼容LocalFullModels.ChineseV4吗?使用LocalFullModels.ChineseV3会提取出乱码,LocalFullModels.ChineseV4会提取出空字符串,但是ONNX使用LocalFullModels.ChineseV4是能正常提取内容的。 ### Describe the solution you'd like . ### Describe alternatives you've considered...

### Describe the bug 以前是老包使用正常,GPU的。 升级最新版依赖包报错Unable to find an entry point named 'PD_ConfigEnableONNXRuntime' in DLL 'paddle_inference_c'.” System.EntryPointNotFoundException:“Unable to find an entry point named 'PD_ConfigEnableONNXRuntime' in DLL 'paddle_inference_c'.” ### Steps to...

### Feature request type sample request ### Is your feature request related to a problem? Please describe 1. Windows 11 环境 2. RTX 4060 8G显卡 3. 安装cuda_11.8.0_522.06_windows.exe 4. 安装cudnn-windows-x86_64-8.6.0.163_cuda11-archive.zip 5....

### Describe the bug 使用GPU,其他模型都是正常的。 using (PaddleDetector detector = new PaddleDetector(modelDir, Path.Combine(modelDir, "infer_cfg.yml"), PaddleDevice.Gpu())) tinypose_128x96模型,报错: Unexpected datatype: Int64 ### Steps to reproduce the bug using (PaddleDetector detector = new PaddleDetector(modelDir,...

### Feature request type sample request ### Is your feature request related to a problem? Please describe The information extraction function is highly practical. Is there any plan to incorporate...

### Describe the bug 可以跑通从官网下载的 ppyoloe 模型。 之后换成了从官网下载并转换格式后的 ppyoloe+ 模型,模型可以被正常加载,但在预测时就报出: 引发的异常:“System.AccessViolationException”(位于 Sdcb.PaddleDetection.dll 中) “System.AccessViolationException”类型的未经处理的异常在 Sdcb.PaddleDetection.dll 中发生 尝试读取或写入受保护的内存。这通常指示其他内存已损坏。 请问这是表示库不支持新版的 ppyoloe+ 模型的意思吗?有什么方法可以使用这个模型呢? ### Steps to reproduce the bug sdcb.PaddleDetection 调用ppyoloe+模型时会报错 ### Expected...

### Describe the bug The path to another library:https://gitee.com/raoyutian/PaddleOCRSharp The running speed of another library is only one tenth of yours I just tested the REC model “”“”c# public class...