sygoing / lffd-with-ncnn Goto Github PK
View Code? Open in Web Editor NEWA C++ API of the LFFD with ncnn
A C++ API of the LFFD with ncnn
RT 单位为ms
Hello,
I modified your code as follows, I have a GPU and Vulkan fully working.
// enable vulkan compute feature before loading
if (useGPU) {
lffd.opt.use_vulkan_compute = true;
}
lffd.load_param(param_file_name.data());
lffd.load_model(bin_file_name.data());
std::cout <<"model loaded, GPU enables?=" << lffd.opt.use_vulkan_compute << std::endl;
However, if I load your model to a GPU it crashes. Everything is fine on a CPU.
Thanks.
原版mxnet是一个.json和一个.param文件.如下:
symbol_file_path = '../symbol_farm/symbol_10_560_25L_8scales_v1_deploy.json'
model_file_path = '../saved_model/configuration_10_560_25L_8scales_v1/train_10_560_25L_8scales_v1_iter_1400000.params'
您的ncnn是一个.param一和个.bin文件,这两个文件怎么来的?用什么工具把上面两个文件转换的来吗?
my picture have many faces,while the code can only find one ,why?
different nms lead to different results.
我用v2版本人脸检测测试的时候显示的错误是slice_axis不支持,我想问下你们用的ncnn是哪一个版本
Hi,
thank you for your contribution.
Could you tell me how you converted the Mxnet model to NCNN?
When I tried the direct conversion using the Mxnet2Ncnn tool, there are layers missing.
Did you convert it to ONNX first?
Would be great if you could share a conversion path.
Thank you!
the bounding box is large and missed most of the faces in the image.
你好,
//x-left-top
float mid_value = 0;
for (int j = 0; j < fea_h * fea_w; j++) {
mid_value = RF_center_Xs_mat[j] - box_map.channel(0)[j] * constant[scale_id];
x_lt_mat[j] = mid_value < 0 ? 0 : mid_value;
}
不太理解这段code坐标值的计算原理( RF_center_Xs_mat[j] - box_map.channel(0)[j] * constant[scale_id];),能否讲解一下呢 不胜感激
how to achieve pedestrian_detection in LFFD-with-ncnn ? How to modify the LFFD.cpp?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.