-
在公司安全可信选型版本发现，我司的ncnn库里只有这个版本是可信的
https://github.com/Tencent/ncnn/releases/download/20200727/ncnn-android-lib.zip
我们用的是yolo做检测，看了ncnn 20200727的修改记录，对应的应该是yolov4
如果要切换改版本，需要做哪些改动？
盼复！
-
### Describe your suggested feature
Often Manga scanlations have a lower resolution than modern phone and tablet screens, which means they will get scaled up while displaying them. This results in …
radry updated
1 month ago
-
I used the r20b to compile the code, but got errors.
///////////////////////////////////////////////////////////////////////////////
Execution failed for task ':app:externalNativeBuildSSDMobilnetDeb…
-
pt转onnx用到 --train
onnx->ncnn用的是pnnx
android端cpp代码，修改了in0,out0,out1,out2,generate_proposals()方法
后附param,bin,cpp（jni）文件,在一个zip里
[assets_and_cpp.zip](https://github.com/Tencent/ncnn/files/9651166/ass…
-
初学者求助...
使用android ndk编译成共享库libncnn.so、libvulkan.so、libmycode.so，编译过程应该是没问题的。大部分代码在android上可以正常运行，例如加载模型、创建ncnn::mat这些都是没问题的...
然而在`ncnn::Mat pha_;ex.extract("pha", pha_);`出现问题了，虽然没有报错，pha_.h和pha_.w…
-
I've run the demo and find that the object detection process runs faster with option "CPU" instead of "GPU".
Is this NORMAL ?
I 'm using:
- ncnn_20210720_android_vulkan
- opencv_mobile_4_5_3_andro…
-
I have converted it to .onnx format using [export.py](http://export.py/) in the yolov8-obb project, with the following command: "python [export.py](http://export.py/) --weights 'runs/train/exp/weights…
-
## 基本概况
NCNN项目首页的README写的非常清楚：
> ncnn 是一个为手机端极致优化的高性能神经网络前向计算框架。ncnn 从设计之初深刻考虑手机端的部署和使用。无第三方依赖，跨平台，手机端 cpu 的速度快于目前所有已知的开源框架。基于 ncnn，开发者能够将深度学习算法轻松移植到手机端高效执行，开发出人工智能 APP，将 AI 带到你的指尖。ncnn 目前已在腾讯多款…
-
ncnn-android-lib.zip 版本为https://github.com/Tencent/ncnn/releases/tag/20210322
#02 pc 000573cd /data/app/com.jinxin.namibox-4_QRJUbw2X4gIYPGhjy50g==/lib/arm/libmtcnn.so (ncnn::Mat::create(int, int…
-
I cloned this repository and I replaced the model in "app\src\main\assets" with one I trained myself on YOLOv7.
I trained it using the "yolov7.pt" weights and the results were great.
I followed the …