Hmrishav Bandyopadhyay

The hyperparameters for reference: ``` PREFIX="--dataset_mode_train trainimage \ --name debugarr0 \ --gpu_ids 0 \ --dataset_mode_val valimage \ --train_image_dir ... \ --train_image_list ... \ --path_objectshape_base ... \ --path_objectshape_list ... \ --val_image_dir...

Works

How many epochs did you run for each stage in the training? The epochs listed in the bash file seem too low. Did you use that low epochs?

Same error even after installing libgles2-mesa-dev ``` (ai) root@gpu-3:~/work# apt install libgles2-mesa-dev Reading package lists... Done Building dependency tree Reading state information... Done libgles2-mesa-dev is already the newest version (20.0.8-0ubuntu1~18.04.1)....

Well, i figured that the file DatasetReader.cpp had a header missing. `#include ` will be submitting a pull request soon :)

Upgraded to python3

Hi, I am interested in this issue. Would passing along a separate marker( bool variable) be enough to avoid this problem? The marker would certify whether the annotations are necessary...

Hi, I would like to work on this. This requires me to just remove and replace the obsolete features in python 2.7 and Tensorflow right?

I have updated to python3.6.9 and will submit the pull request to the same. I hope it is alright to solve this part by part.

Yes, but i have actually not created a branch from master in my fork of the project before committing and now i cant commit before the pull request is merged...