according to the official documentationDeep Learning accuracy validation framework ,I install the tool accuracy checker and prepare to run the sample to test my installation. There is an ERROR about the main.py file and I dont know WHY. If anyone can help me and thanks.
I have run successfully the sample demo, now I am working on my own model and datasets, and there are some PROBLEMS need to be solved.
In the accuracy checker. I need to describe the Dataset entry in my file of accuracy-checke.yml or we can name the file with the model name. Because I use my own dataset with the format of VOCdevkit2007, I imitate the format and files like voc_detection .But I dont know where to set my dataset and where is the converted dataset.
the ERROR is showed as teh follow.
accuracy check -c /opt/intel/openvino 2019.3.334/dep|loyment tools/open model _zoo/models/public/mobilenet-yolo-syg/accuracy-check.yml-m o mz-test-s omz-test/VoCdevkit accuracycheck/VOC2007/-a omz-test/vocdevkit accuracych eck/VOC2007/Annotations/
the file is opened with notepad++
THANKS for applying me , The format error in my yaml file has been solved.
now there is ERROR in my yaml file， maybe it isrelated to the launcher which I dont use very well.
thanks for helping me and your excellent reply.
the command is accuracy_check -c /opt/intel/openvino_2019.3.334/deployment_tools/open_model_zoo/models/public/mobilenet-yolo-syg/accuracy-check.yml -m omz-test -s omz-test/VOCdevkit_accuracycheck -a omz-test
It seems from the error message "cannot parse future versions" means that the IR model file you are using is created using newer version of OpenVINO.
You would need to use models created from the same OpenVINO version or older.
Alternatively, I would recommend you to get either the Long Term Support version or the latest version.
What are the differences in the overall usage of the model transformed with the newer version compared to the older version of OPENVINO? Assuming that the IR model comes from someone else, how do I know which version is converted? and how can I use it better?
I have solved some probems,but I faced new one. Thank you for your careful and earnest reply.
I run the yolo-v3-tf models,which is in the open model zoo，but I cant the right map value. The yolo3-omz dictionary includes all the files the command needs which are copied in the open model zoo.
accuracy_check -c /opt/intel/openvino_2020.3.341/deployment_tools/open_model_zoo/tools/accuracy_checker/configs/yolo-v3-tf.yml -m yolo3-omz -s yolo3-omz -a yolo3-omz -td cpu
I have replicated your case on my device and found no issue. I suggest you check back your model and program. Please note to follow the steps of 'example of usage' on this page.
This thread will no longer be monitored since we have provided a solution. If you need any additional information from Intel, please submit a new question.