Skip to content

Commit

Permalink
Improved AutoBatch DDP error message (#6568)
Browse files Browse the repository at this point in the history
* Improved AutoBatch DDP error message

* Cleanup
  • Loading branch information
glenn-jocher authored Feb 8, 2022
1 parent b57abb1 commit 006eb40
Showing 1 changed file with 5 additions and 3 deletions.
8 changes: 5 additions & 3 deletions train.py
Original file line number Diff line number Diff line change
Expand Up @@ -522,10 +522,12 @@ def main(opt, callbacks=Callbacks()):
# DDP mode
device = select_device(opt.device, batch_size=opt.batch_size)
if LOCAL_RANK != -1:
msg = 'is not compatible with YOLOv5 Multi-GPU DDP training'
assert not opt.image_weights, f'--image-weights {msg}'
assert not opt.evolve, f'--evolve {msg}'
assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size'
assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE'
assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command'
assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count'
assert not opt.image_weights, '--image-weights argument is not compatible with DDP training'
assert not opt.evolve, '--evolve argument is not compatible with DDP training'
torch.cuda.set_device(LOCAL_RANK)
device = torch.device('cuda', LOCAL_RANK)
dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo")
Expand Down

0 comments on commit 006eb40

Please sign in to comment.