Traceback (most recent call last):
File “D:\pythonProject\MatchFormer-main\test.py”, line 57, in
trainer.test(model, datamodule=data_module, verbose=False)
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\trainer.py”, line 794, in test
return call._call_and_handle_interrupt(
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\call.py”, line 38, in _call_and_handle_interrupt
return trainer_fn(*args, **kwargs)
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\trainer.py”, line 842, in _test_impl
results = self._run(model, ckpt_path=self.ckpt_path)
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\trainer.py”, line 1051, in _run
self._call_setup_hook() # allow user to setup lightning_module in accelerator environment
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\trainer.py”, line 1298, in _call_setup_hook
self._call_lightning_datamodule_hook(“setup”, stage=fn)
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\pytorch_lightning\trainer\trainer.py”, line 1375, in _call_lightning_datamodule_hook
return fn(*args, **kwargs)
File “D:\pythonProject\MatchFormer-main\model\data.py”, line 116, in setup
self.world_size = dist.get_world_size()
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\torch\distributed\distributed_c10d.py”, line 1067, in get_world_size
return _get_group_size(group)
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\torch\distributed\distributed_c10d.py”, line 453, in _get_group_size
default_pg = _get_default_group()
File “D:\anaconda\anaconda4\envs\pytorch-gpu\lib\site-packages\torch\distributed\distributed_c10d.py”, line 584, in _get_default_group
raise RuntimeError(
RuntimeError: Default process group has not been initialized, please make sure to call init_process_group.
Did you initialize the process group as explained in the error message?
I would also recommend changing the topic title to a give more information about your error so that more experienced users might want to help out.