Missing 'Detector' attribute

[Stanley-Michael]

Specs:

Tesla T4
CUDA Version 11.6
Driver Version: 510.47.03
Client: Docker Engine - Community
Version: 20.10.17
API version: 1.41

Steps done:

Pull docker file:
docker pull cvisionai/openem_lite:latest

Launch the docker env:
nvidia-docker run --name openem --rm -ti --shm-size=1g --ulimit memlock=-1 --ulimit stack=67108864 -v /project/:/project -v /data:/data cvisionai/openem_lite bash

cd to openem/train

python3 train.py train.ini find_ruler_predict

Extracting ROIs ***

python train.py train.ini extract_rois

Issue: 
  File "/project/openem/train/openem_train/preprocess.py", line 166, in _extract_roi
  img = openem.Image()
  AttributeError: module 'openem' has no attribute 'Image'

Inferece - Detection

python3 train.py train.ini detect_predict

Issue: 
AttributeError: module 'openem' has no attribute 'Detector'

Both the extraction of ROI's and the Detection fail.

I am using the pretrained models included in the tutorial, and using the docker image with a python virtual env for installing the deployment library (from deploy_python).