dongfangduoshou123 / caffe2-yolo-v3 Goto Github PK
View Code? Open in Web Editor NEWA Caffe2 implementation of the YOLO v3 object detection algorithm
A Caffe2 implementation of the YOLO v3 object detection algorithm
Hi,
could you specify on what license is this project?
It's great but I'm not sure if I can use it without a license.
Best Regards,
Paweł
Hi looks like the .pbtxt files are not OK - I cannot read them...?
I'm trying to read them like this:
device_opts = core.DeviceOption(caffe2_pb2.CPU)
net_def = caffe2_pb2.NetDef()
filename_prefix = 'param_init_net'
with open(filename_prefix+'.pbtxt', 'r') as f:
file_content = f.read()
text_format.Merge(file_content, net_def, True, True)
with open(filename_prefix+'.pb', "wb") as fout:
fout.write(net_def.SerializeToString())
Do you have them in .PB format?
Thanks,
N
I've compiled it successfully and can run the python example properly. But the main.cpp file keeps reporting errors。I found error in Line 86:CAFFE_ENFORCE(workspace.RunNet(predictnet.name()));
and GetTensorToHost function in boxuitl.h . I can't make it. Can you help me? Thanks!
The error is :
terminate called after throwing an instance of 'std::length_error'
what(): vector::_M_default_append
Aborted (core dumped)
Here is my compilation error output
[ 93%] Building NVCC (Device) object modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/caffe2_yolo_ops_gpu_generated_yolo_op.cu.o
/home/gpuhuawei/tools/pytorch/modules/Yolo/yolo_op.h(49): error: class "caffe2::Tensor" may not have a template argument list
/home/gpuhuawei/tools/pytorch/modules/Yolo/yolo_op.h(54): error: class "caffe2::Tensor" may not have a template argument list
/home/gpuhuawei/tools/pytorch/modules/Yolo/yolo_op.h(60): error: class "caffe2::Tensor" may not have a template argument list
/home/gpuhuawei/tools/pytorch/modules/Yolo/yolo_op.h(52): error: type name is not allowed
/home/gpuhuawei/tools/pytorch/modules/Yolo/yolo_op.h(52): error: expected an expression
5 errors detected in the compilation of "/tmp/tmpxft_000075e5_00000000-7_yolo_op.compute_35.cpp1.ii".
CMake Error at caffe2_yolo_ops_gpu_generated_yolo_op.cu.o.Release.cmake:279 (message):
Error generating file
/home/gpuhuawei/tools/pytorch/build/modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir//./caffe2_yolo_ops_gpu_generated_yolo_op.cu.o
modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/build.make:70: recipe for target 'modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/caffe2_yolo_ops_gpu_generated_yolo_op.cu.o' failed
make[2]: *** [modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/caffe2_yolo_ops_gpu_generated_yolo_op.cu.o] Error 1
CMakeFiles/Makefile2:5031: recipe for target 'modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/all' failed
make[1]: *** [modules/Yolo/CMakeFiles/caffe2_yolo_ops_gpu.dir/all] Error 2
make[1]: *** Waiting for unfinished jobs....
Can you fix it?
I want to know how to convert the "*.weights" file to the model file? is there any tools or projects? Thanks very much!
Hi
I have caffe2 install on my machine (i.e. python "import caffe2" works) and want to test run the demo.py.
I am confused about your description in the first step of Intall the YOLOModule.
In order to create the libcaffe2_yolo_ops_gpu.so, what do you mean by "cut yolo page to module folder"?
FYI,I install the caffe2 from caffe2.ai using conda install
Where can I load the path of my existing caffe2?
If you happen to speak Chinese, more than welcome to answer it in Chinese.
Thanks
大佬如何在win10下测试你的cppdemo?没有.so文件
Hi Sir,
I cannot download model files via https://pan.baidu.com/s/1ykYOJgMVXlgACXMC5jAMOQ ,
Could you share the model files again ?
Thanks,
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.