The facerecognition_mtcnn_facenet from chanstk

prediction accurate

hello,chan,I'm using your code to make predictions, but I find that the accuracy of the prediction is very low. Is that the same for you? thank you

crashing with opencv4

the program is crashing in following line
Image = Image - cv::Vec3d(mean_pxl, mean_pxl, mean_pxl);
please help me to fix the issue

tensorflow/core/framework/graph.pb.h no such file

hello ,when I run your program the error ' tensorflow/core/framework/graph.pb.h no such file' will be taken.I want to know where I can get this file. https://github.com/tensorflow/tensorflow doesn't have.

set_per_process_gpu_memory_fraction cause Segmentation fault

Hi,
Have you try to limit the GPU memory usage?
I just use GTX1070 which has 8G memory and config the GPU memory using the following code

void getSession(string graph_path, std::unique_ptr<tensorflow::Session> &session){
     tensorflow::GraphDef graph_def;
     if (!ReadBinaryProto(tensorflow::Env::Default(), graph_path, &graph_def).ok()) {
         LOG(ERROR) << "Read proto";
         return ;
     }
     tensorflow::SessionOptions sess_opt;
     sess_opt.config.mutable_gpu_options()->set_per_process_gpu_memory_fraction(0.8);
 
     (&session)->reset(tensorflow::NewSession(sess_opt));
 
     if (!session->Create(graph_def).ok()) {
         LOG(ERROR) << "Create graph";
         return ;
     }
 }

But when I generate the binary file and run it, the program got:

/opt/tf_test/FaceRecognition_MTCNN_FaceNet
2017-12-28 17:48:06.721839: I tensorflow/core/platform/cpu_feature_guard.cc:137] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2017-12-28 17:48:06.904772: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2017-12-28 17:48:06.905343: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1202] Found device 0 with properties: 
name: GeForce GTX 1070 major: 6 minor: 1 memoryClockRate(GHz): 1.645
pciBusID: 0000:01:00.0
totalMemory: 7.92GiB freeMemory: 7.11GiB
2017-12-28 17:48:06.905357: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1296] Adding visible gpu device 0
Segmentation fault (core dumped)

Thank you very much.

chanstk / facerecognition_mtcnn_facenet Goto Github PK

facerecognition_mtcnn_facenet's People

Contributors

Stargazers

Watchers

Forkers

facerecognition_mtcnn_facenet's Issues

prediction accurate

crashing with opencv4

tensorflow/core/framework/graph.pb.h no such file

set_per_process_gpu_memory_fraction cause Segmentation fault

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent

Jobs