Nikesh Devkota

The issue seems to be due to the pyqt5 version. I just uninstalled the latest version of pyqt5 and installed pyqt 5.12.3 and labelIng worked. I had also put python3.dll...

@mj1156 can you provide details on how you set up a pipeline to load data for a custom dataset?

@elsa-1920 did you find out how we can load the datasets using the CSV format?

@adavradou did you find the solution? I also tried to load it from tf.data.Dataset.from_generator but got a NAN value in loss immediately. @srihari-humbarwadi any solution for this?

@rpsantosa @X-F-Lpro could you guys provide a little bit more detail about implementing the RetinaNet on custom dataset

 I have a csv file which has an annotation format as follows: "path to image","xmin","ymin","xmax","ymax","class ID","class name" and I am trying to load the data in the same format...

@X-F-Lpro I am detecting object detection for small target, so I will change the anchor box size accordingly as well.

I also tried installing the package in Ubuntu 18.04 that has a NVIDIA GeForce RTX 3080 but found out it was incompatible with CUDA below 11.1. Is there any solution...

Thank you @timmeinhardt , I will check the repo.

I couldn't solve the error in Windows and the GPU I had in Linux was not compatible with the original repository. So, as @timmeinhardt suggested I used the pytorch version...