Panoptic Segmentation Error for 100-5

[kmn5409]

Why is train_net.py used to create the base model? This can be seen here

When I try and train the base model using this code I encounter the error

Traceback (most recent call last):
  File "train_net.py", line 343, in <module>
    launch(
  File "/projectnb/ivc-ml/kmn5409/environments/comformer/lib/python3.8/site-packages/detectron2/engine/launch.py", line 82, in launch
    main_func(*args)
  File "train_net.py", line 334, in main
    ret = trainer.train()
  File "/projectnb/ivc-ml/kmn5409/environments/comformer/lib/python3.8/site-packages/detectron2/engine/defaults.py", line 484, in train
    super().train(self.start_iter, self.max_iter)
  File "/projectnb/ivc-ml/kmn5409/environments/comformer/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 149, in train
    self.run_step()
  File "/projectnb/ivc-ml/kmn5409/environments/comformer/lib/python3.8/site-packages/detectron2/engine/defaults.py", line 494, in run_step
    self._trainer.run_step()
  File "/projectnb/ivc-ml/kmn5409/environments/comformer/lib/python3.8/site-packages/detectron2/engine/train_loop.py", line 400, in run_step
    losses = sum(loss_dict.values())
TypeError: unsupported operand type(s) for +: 'int' and 'dict'
scripts/adps5.sh: line 33: syntax error near unexpected token `done'

However it works when I utilize the train_inc.py but I am not able to reproduce the same results, as was stated in the other github issue

[hanminpay]

I encountered the same problem