Styjun

Earliest evidence of objects intended for future archaeologists?

Repurpose telephone line to ethernet

Does == actually work the same or different when comparing two primitives vs two Objects in Java?

To plot branch cut of logarithm

Installing certbot - error - "nothing provides pyparsing"

What causes burn marks on the air handler in the attic?

How to add a table description to a longtable?

Do banks' profitability really suffer under low interest rates

Is there a utility / method to organize trad gear so that each piece is immediately accessible?

Reducing contention in thread-safe LruCache

Why should I pay for an SSL certificate?

What security risks does exposing the size of the plaintext entail?

Peterhead Codes and Ciphers Club: Weekly Challenge

Starships without computers?

Have made several mistakes during the course of my PhD. Can't help but feel resentment. Can I get some advice about how to move forward?

Why is su world executable?

The anatomy of an organic infrared generator

Linear and Integer programming materials

Will some rockets really collapse under their own weight?

Virtual destructor moves object out of rodata section

Airline power sockets shut down when I plug my computer in. How can I avoid that?

Why should P.I be willing to write strong LOR even if that means losing a undergraduate from his/her lab?

Designing a prison for a telekinetic race

Would getting a natural 20 with a penalty still count as a critical hit?

“Unknown layer type: net in function” when loading yolov3 using OpenCV's DNN library

OpenCV's clustering function cvKMeans2() - what is a type of cluster center in array?OpenCV's clustering function cvKMeans2() - why doesnt work when i use the centers parameterOpenCV Error: Bad argument <Unknown array type> in unknown function, file ......modulescoresrcmatrix.cpp, line 697Different matching results for opencv's descriptor_extractor_matcher when loading data from fileError when using two flags OpenCv's calibrateCamera functionOpenCV - Unknown array type in function cvarrToMatParsing the cfg file froom YOLO-Darknet in OpenCV DNNOpenCV unknown layer type running darknet detectopencv dnn load darknet unknow layer type sseProblems using cv::dnn::Layer cv::dnn::LayerFactory and cv::dnn::Net

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

0

I am attempting to use Yolov3 using OpenCV's (4.0.1) DNN Library on MacOs in C++. I am trying to use cv::dnn::readNetFromDarknet to load the yolov3.cfg file but I am getting this error :

"(-212:Parsing error) Unknown layer type: net in function
'ReadDarknetFromCfgStream'"

I've made sure the yolov3.cfg that is within my project matches up with the one on the web https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg which it does. If I change " [net] " to something else for example " [layer] " then the error will change to :

"(-212:Parsing error) Unknown layer type: layer in function
'ReadDarknetFromCfgStream'"

Almost as if either the cfg file is wrong or opencv is not reading it correctly.

The start of the config file looks like this :

[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=16
width=608
height=608
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

which is where I assume the problem is.

My code for loading the net is :

const char * pathStart = gGetRootAppPath();
pathEnd = "/yolo/yolov3.cfg";
std::string modelConfiguration = pathStart + pathEnd;
pathEnd = "/yolo/yolov3.weights";
std::string modelWeights = pathStart + pathEnd;

//set up the neural network
cv::dnn::readNetFromDarknet(modelConfiguration,modelWeights);

Any help would be much appreciated.

opencv yolo darknet

share|improve this question

edited Mar 28 at 17:09

Joachim.A

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  try to use absolute path, dont use const char * pathStart = gGetRootAppPath()
  
  – gameon67
  Mar 28 at 0:16
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  thanks @gameon67, I've tried that but I'm still getting the same problem.
  
  – Joachim.A
  Mar 28 at 8:45
  

  
  
  
  

add a comment | 

0

I am attempting to use Yolov3 using OpenCV's (4.0.1) DNN Library on MacOs in C++. I am trying to use cv::dnn::readNetFromDarknet to load the yolov3.cfg file but I am getting this error :

"(-212:Parsing error) Unknown layer type: net in function
'ReadDarknetFromCfgStream'"

I've made sure the yolov3.cfg that is within my project matches up with the one on the web https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg which it does. If I change " [net] " to something else for example " [layer] " then the error will change to :

"(-212:Parsing error) Unknown layer type: layer in function
'ReadDarknetFromCfgStream'"

Almost as if either the cfg file is wrong or opencv is not reading it correctly.

The start of the config file looks like this :

[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=16
width=608
height=608
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

which is where I assume the problem is.

My code for loading the net is :

const char * pathStart = gGetRootAppPath();
pathEnd = "/yolo/yolov3.cfg";
std::string modelConfiguration = pathStart + pathEnd;
pathEnd = "/yolo/yolov3.weights";
std::string modelWeights = pathStart + pathEnd;

//set up the neural network
cv::dnn::readNetFromDarknet(modelConfiguration,modelWeights);

Any help would be much appreciated.

opencv yolo darknet

share|improve this question

edited Mar 28 at 17:09

Joachim.A

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  try to use absolute path, dont use const char * pathStart = gGetRootAppPath()
  
  – gameon67
  Mar 28 at 0:16
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  thanks @gameon67, I've tried that but I'm still getting the same problem.
  
  – Joachim.A
  Mar 28 at 8:45
  

  
  
  
  

add a comment | 

I am attempting to use Yolov3 using OpenCV's (4.0.1) DNN Library on MacOs in C++. I am trying to use cv::dnn::readNetFromDarknet to load the yolov3.cfg file but I am getting this error :

"(-212:Parsing error) Unknown layer type: net in function
'ReadDarknetFromCfgStream'"

I've made sure the yolov3.cfg that is within my project matches up with the one on the web https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg which it does. If I change " [net] " to something else for example " [layer] " then the error will change to :

"(-212:Parsing error) Unknown layer type: layer in function
'ReadDarknetFromCfgStream'"

Almost as if either the cfg file is wrong or opencv is not reading it correctly.

The start of the config file looks like this :

[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=16
width=608
height=608
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

which is where I assume the problem is.

My code for loading the net is :

const char * pathStart = gGetRootAppPath();
pathEnd = "/yolo/yolov3.cfg";
std::string modelConfiguration = pathStart + pathEnd;
pathEnd = "/yolo/yolov3.weights";
std::string modelWeights = pathStart + pathEnd;

//set up the neural network
cv::dnn::readNetFromDarknet(modelConfiguration,modelWeights);

Any help would be much appreciated.

opencv yolo darknet

share|improve this question

edited Mar 28 at 17:09

Joachim.A

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

"(-212:Parsing error) Unknown layer type: net in function
'ReadDarknetFromCfgStream'"

"(-212:Parsing error) Unknown layer type: layer in function
'ReadDarknetFromCfgStream'"

[net]
# Testing
# batch=1
# subdivisions=1
# Training
batch=64
subdivisions=16
width=608
height=608
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1

learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1

const char * pathStart = gGetRootAppPath();
pathEnd = "/yolo/yolov3.cfg";
std::string modelConfiguration = pathStart + pathEnd;
pathEnd = "/yolo/yolov3.weights";
std::string modelWeights = pathStart + pathEnd;

//set up the neural network
cv::dnn::readNetFromDarknet(modelConfiguration,modelWeights);

share|improve this question

edited Mar 28 at 17:09

Joachim.A

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

share|improve this question

edited Mar 28 at 17:09

Joachim.A

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges

asked Mar 27 at 13:59

Joachim.AJoachim.A

122 bronze badges