Comments (8)
Have you solved the problem?I have the same problem.
from darknet_face_with_landmark.
i had solved the problem, pull and make it.
from darknet_face_with_landmark.
i had solved the problem, pull and make it.
Dear author,Could you please share your solution?
thank you.
from darknet_face_with_landmark.
@timohaha add HSWISH and HSIGMODE to darknet.h
from darknet_face_with_landmark.
@timohaha add HSWISH and HSIGMODE to darknet.h
i know。but when i changed darknet.h file. Other problems arose.
./src/yolo_layer.c: In function ‘forward_yolo_layer’: ./src/yolo_layer.c:479:25: warning: variable ‘best_match_t’ set but not used [-Wunused-but-set-variable] int best_match_t = 0; ^ ./src/yolo_layer.c:724:21: error: ‘for’ loop initial declarations are only allowed in C99 mode for (int i = 0 ; i< l.classes + 1 ; i++){ ^ compilation terminated due to -Wfatal-errors. Makefile:162: recipe for target 'obj/yolo_layer.o' failed make: *** [obj/yolo_layer.o] Error 1
from darknet_face_with_landmark.
It works for me now, thanks!
from darknet_face_with_landmark.
Also, what is the logic in your cfg file?
I was trying to run the model in Alexey, the filters before every yolo layer should be
(class+coords+1)*mask right? But when I change it doesn't work.
So I guess here is
(1+coords+1) = 16, why do you have 14 coords? And where in the code I can read to understand and customize these settings?
Thank you!
from darknet_face_with_landmark.
you can comparre my code with https://github.com/AlexeyAB/darknet , the data.c and yolo_layer.c should be change , now only support 5 point
from darknet_face_with_landmark.
Related Issues (20)
- Please let me know how to make data (data format) to train this model ?
- where is your data? HOT 1
- 训练时报错Warning: in txt-label class_id = -2147483648 > classes=1 in cfg-file HOT 3
- hi,我想请问下训练中期会报错吗,我训练中期会突然停止出现下面的错误 HOT 30
- 这里 i 是不是有问题? HOT 4
- the test performance is worse than your's HOT 3
- The inference speed is slower than yolov3 HOT 3
- torch写错了 HOT 1
- Are there pretrained weights HOT 1
- 训练过程中,读取图片的过程中,线程一直等待,无法继续训练问题 HOT 1
- 关于步骤2:"使用scripts/retinaface2yololandmark.py脚本将retinaface的标记文件转为yolo的格式"的问题 HOT 1
- Face detective img crop HOT 2
- 关键点检测
- 关于num outputs问题 HOT 3
- *** Error in `./darknet': double free or corruption (out): 0x00007f1910a06010 *** HOT 2
- training problem
- widerface val
- 請問您訓練出mbv3small_yolov3_face.weights 如何先取得預訓練的? HOT 1
- I change 5 points to 98 points,cfg and code need change? and change where? HOT 1
- 请问yolo的检测结果如何在widerface上进行测试呢
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from darknet_face_with_landmark.