Pavan Tripathi
Pavan Tripathi
got it resolved. first used try except for checking if i was able to import required package. try: from lxml import etree print("running with lxml.etree !") except ImportError: print("Import etree...
Same issue on my end. I am using an ONNX model and the results vary slightly
Hello @HauJulian, were you able to figure this out? I am facing the same issue as well.
I was able to solve it. My problem was that the confidence value of my detections were difference in python and cpp. It was sometimes >200 in CPP. In case...
also check if your config file has this parameter, keep_ratio: False. If this is the case, you will have to change main.cpp  ``` dst = cv::Mat(cv::Size(dst_w, dst_h), CV_8UC3, cv::Scalar(0));...
I fixed my threshold using hit and trial method. Check which particular values are giving you the best results and fix them as per that. Happy to see that it...
Same error here. Was anyone able to resolve this?
This is due to version mismatch. Change your requirements.txt with this : Cython matplotlib numpy omegaconf>=2.0.1 onnx onnx-simplifier opencv-python pyaml pycocotools pytorch-lightning>=1.9.0,
Same issue on my end. Did you find the solution to this issue?
I solved this by commenting line 135,136 in main/nanodet/model/head/nanodet_plus_head.py.