Browse Source

Improved AutoBatch DDP error message (#6568)

* Improved AutoBatch DDP error message

* Cleanup
modifyDataloader
Glenn Jocher GitHub 2 years ago
parent
commit
006eb40ab7
No known key found for this signature in database GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 3 deletions
  1. +5
    -3
      train.py

+ 5
- 3
train.py View File

@@ -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")

Loading…
Cancel
Save