Update DDP for torch.distributed.run with gloo backend (#3680)

* Update DDP for `torch.distributed.run`

* Add LOCAL_RANK

* remove opt.local_rank

* backend="gloo|nccl"

* print

* print

* debug

* debug

* os.getenv

* gloo

* gloo

* gloo

* cleanup

* fix getenv

* cleanup

* cleanup destroy

* try nccl

* return opt

* add --local_rank

* add timeout

* add init_method

* gloo

* move destroy

* move destroy

* move print(opt) under if RANK

* destroy only RANK 0

* move destroy inside train()

* restore destroy outside train()

* update print(opt)

* cleanup

* nccl

* gloo with 60 second timeout

* update namespace printing

test.py

@@ -51,7 +51,6 @@ def test(data,
         device = next(model.parameters()).device  # get model device
 
     else:  # called directly
-        set_logging()
         device = select_device(device, batch_size=batch_size)
 
         # Directories
@@ -323,7 +322,8 @@ def parse_opt():
 
 
 def main(opt):
-    print(opt)
+    set_logging()
+    print(colorstr('test: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
     check_requirements(exclude=('tensorboard', 'thop'))
 
     if opt.task in ('train', 'val', 'test'):  # run normally