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

detect.py

@@ -8,8 +8,8 @@ import torch.backends.cudnn as cudnn
 
 from models.experimental import attempt_load
 from utils.datasets import LoadStreams, LoadImages
-from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
-    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
+from utils.general import check_img_size, check_requirements, check_imshow, colorstr, non_max_suppression, \
+    apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
 from utils.plots import colors, plot_one_box
 from utils.torch_utils import select_device, load_classifier, time_synchronized
 
@@ -202,7 +202,7 @@ def parse_opt():
 
 
 def main(opt):
-    print(opt)
+    print(colorstr('detect: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
     check_requirements(exclude=('tensorboard', 'thop'))
     detect(**vars(opt))