wzj5133329 / retinaface_caffe Goto Github PK
View Code? Open in Web Editor NEW完整版caffe-cpp实现
完整版caffe-cpp实现
why resize all input to size "input_geometry_"?
Does the Input img must be a fixed size?
I1217 08:19:26.450222 6021 layer_factory.hpp:77] Creating layer mobilenet0_relu8
I1217 08:19:26.450242 6021 net.cpp:86] Creating Layer mobilenet0_relu8
I1217 08:19:26.450255 6021 net.cpp:408] mobilenet0_relu8 <- mobilenet0_batchnorm8
I1217 08:19:26.450273 6021 net.cpp:369] mobilenet0_relu8 -> mobilenet0_batchnorm8 (in-place)
I1217 08:19:26.459385 6021 net.cpp:124] Setting up mobilenet0_relu8
I1217 08:19:26.459436 6021 net.cpp:131] Top shape: 1 64 8 10 (5120)
I1217 08:19:26.459461 6021 net.cpp:139] Memory required for data: 1332480
I1217 08:19:26.459479 6021 layer_factory.hpp:77] Creating layer mobilenet0_conv9
I1217 08:19:26.459518 6021 net.cpp:86] Creating Layer mobilenet0_conv9
I1217 08:19:26.459537 6021 net.cpp:408] mobilenet0_conv9 <- mobilenet0_batchnorm8
I1217 08:19:26.459563 6021 net.cpp:382] mobilenet0_conv9 -> mobilenet0_conv9
F1217 08:19:28.327307 6021 cudnn_conv_layer.cpp:53] Check failed: status == CUDNN_STATUS_SUCCESS (4 vs. 0) CUDNN_STATUS_INTERNAL_ERROR
*** Check failure stack trace: ***
Aborted (core dumped)
does anyone know the reason?
I0809 11:51:02.075692 7224 upgrade_proto.cpp:80] Successfully upgraded batch norm layers using deprecated params.
channels3
img10480
F0809 11:51:02.320047 7224 syncedmem.cpp:56] Check failed: error == cudaSuccess (2 vs. 0) out of memory
看了一下显存是满了,改哪里可以使降显存吗?
请问该bug应该怎么解决呢?
您好。我按照你的要求修改了Makefile文件,把我的caffe路径添加进去了,在make时出现了错误:
g++ -o retinaface detect.o anchor_generator.o config.o tools.o main.o -lboost_system -lcaffe -lglog -lprotobuf -lcudart -lgflags
pkg-config opencv
/usr/bin/ld: cannot find -lcaffe
/usr/bin/ld: cannot find -lcudart
collect2: error: ld returned 1 exit status
Makefile:21: recipe for target 'retinaface' failed
make: *** [retinaface] Error 1`
请问您是怎么解决的,谢谢你了。
您好,我分别用您的模型和官方的mnet.25 跑了一下,看到您的模型shape是1920x1080,而官方给出的shape是640x640,
我正在梳理是哪里出了问题,
您能告诉我您是从哪个模型转成的caffe模型吗?
您好, 您用的opencv版本是哪个,谢谢
net_.reset(new Net(model_file, TEST)); running to mobilenet0_conv26
error occurs
Why???
在caffe-cpu下运行程序,在
void AnchorGenerator::landmark_pred(const CRect2f anchor, const std::vectorcv::Point2f& delta, std::vectorcv::Point2f& pts) {
float w = anchor[2] - anchor[0] + 1;
float h = anchor[3] - anchor[1] + 1;
float x_ctr = anchor[0] + 0.5 * (w - 1);
float y_ctr = anchor[1] + 0.5 * (h - 1);
pts.resize(delta.size());
for (int i = 0; i < delta.size(); ++i) {
pts[i].x = (delta[i].x*w + x_ctr)ratiow;
pts[i].y = (delta[i].yh + y_ctr)*ratioh;
}
}中出现以下问题, 请问是什么原因? @wzj5133329
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.