KK Cheung

Cross compiling to arm linux platform : Segmentation fault (core dumped)

6

I am doing cross compiling to arm linux platform. I don't need these modules like viz, sfm,freetype etc. But now I have to add these so libraries to compile. ...

Make sure the SurfaceView or associated SurfaceHolder has a valid Surface

3

请问这个问题是什么原因？ 我没有看到有指定设备id的相关代码，是不是如果有多设备必须使用多路的调用方式？ ``` E FATAL EXCEPTION: gl_render Process: com.example.triscdemo, PID: 25890 java.lang.IllegalArgumentException: Make sure the SurfaceView or associated SurfaceHolder has a valid Surface at android.opengl.EGL14._eglCreateWindowSurface(Native Method) at android.opengl.EGL14.eglCreateWindowSurface(EGL14.java:263) at com.jiangdg.ausbc.render.env.EGLEvn.setupSurface(EGLEvn.kt:101)...

python 3.8 并不支持 onnx=1.6.0 吧？ https://github.com/onnx/onnx/issues/2734 我对 METADATA 做了以下修改才安装通过 ``` Requires-Dist: onnx (>=1.6.0) ```

## yolov5 python convert.py /home/nianqing/try/anitnet-export/exp12/weights/best.onnx rv1126 u8 转换成功，加载失败 python yolov5.py --model_path ../model/yolov5.rknn --target rv1126 --device_id b9467c6be2237e7a ``` use anchors from '../model/anchors_yolov5.txt', which is [[[10.0, 13.0], [16.0, 30.0], [33.0, 23.0]], [[30.0,...

目前的onnxruntime 会出现以下错误： ``` Traceback (most recent call last): File "../../../../../common/rknn_converter/rknn_convert.py", line 182, in convert(config_dict, args) File "../../../../../common/rknn_converter/rknn_convert.py", line 134, in convert model_runer = Excuter(framework_excute_info) File "/home/abc/xxx/rknn_model_zoo/common/framework_excuter/excuter.py", line 46, in __init__...

[bug] 403 in tauri v2 where I used `convertFileSrc`

4

### Describe the bug ``` const selected = await open({ multiple: false, directory: true, }); ``` let entities = await readDir(selected) //... // for entities let filepath = await join(selected,entity.name)...

No matching distribution found for lancedb==0.6.10

8

Although the file declares support for Python 3.8, https://github.com/lancedb/lancedb/blob/431f94e5644936e67298e81285c76d8fd1858d29/python/pyproject.toml#L21. But i received the following error: ``` ERROR: Could not find a version that satisfies the requirement lancedb==0.6.10 (from -r /app/requirements.txt...

量化的数据集列表是否支持 npy？

1

正确的模型确实只需要图片列表就支持了，因为多数模型的输入都是[1,3,x,x], 但是有一些模型只能并不是这样的，有可能是多张图片合并在通道上，比如2 张合并 [1,6,x,x]，这时候如何处理？ 我试了把 2 张图片合成[6,x,x] 再保存到 npy，作为 dataset list，发现行不通。 似乎也没有开放如何处理 dataset 的接口处理。