-
我打包的程序：
{
"version": "0.1.0",
"files": [
{
"address": 0,
"bin": "LFFD-LP-K210.bin",
"sha256Prefix": true
},
{
"address": 0x00A00000,
"bin": "LP…
-
你好，我在lffd-ncnn里看到一段code
//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] = m…
-
hello, when i use your command to complie，have some issues
when " cmake .. " no errors
when "mkae " have error as follow:
make install
Scanning dependencies of target mlpr
[ 6%] Buildi…
-
I saw other issues that report a very slow network. I tested and got extremely low FPS when detecting faces. There is any plan to release the faster version?
-
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, I have tried to reproduce your results of LFFD v1 on the WIDER_FACE_val dataset.
The training data I used is produced by your method:
1. Input the WIDER FACE train dataset (downloaded from the …
-
Provided code : python configuration_10_320_20L_5scales_v2.py
Provided data : widerface_train_data_gt_8.pkl
At begining, train loss converge normal. iteration times 3400, loss was divergent to nan.…
dtiny updated
3 years ago
-
Hi, I have a question. When I was training my data set, I found that loss concussion was severe. Is this a normal phenomenon? I use the yolox_m , turned off data enhancement，batchsize = 4. The specifi…
-
Could you share the pretrained weight of this model?
Thanks
-
如何用头部检测模型测试自己的图片呢？一直找不到