HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

27
ultralytics/utils/dist.py
View file

@ -18,13 +18,13 @@ def find_free_network_port() -> int:
`MASTER_PORT` environment variable.
"""
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
s.bind(('127.0.0.1', 0))
s.bind(("127.0.0.1", 0))
return s.getsockname()[1] # port
def generate_ddp_file(trainer):
"""Generates a DDP file and returns its file name."""
module, name = f'{trainer.__class__.__module__}.{trainer.__class__.__name__}'.rsplit('.', 1)
module, name = f"{trainer.__class__.__module__}.{trainer.__class__.__name__}".rsplit(".", 1)
content = f"""
# Ultralytics Multi-GPU training temp file (should be automatically deleted after use)
@ -39,13 +39,15 @@ if __name__ == "__main__":
trainer = {name}(cfg=cfg, overrides=overrides)
results = trainer.train()
"""
(USER_CONFIG_DIR / 'DDP').mkdir(exist_ok=True)
with tempfile.NamedTemporaryFile(prefix='_temp_',
suffix=f'{id(trainer)}.py',
mode='w+',
encoding='utf-8',
dir=USER_CONFIG_DIR / 'DDP',
delete=False) as file:
(USER_CONFIG_DIR / "DDP").mkdir(exist_ok=True)
with tempfile.NamedTemporaryFile(
prefix="_temp_",
suffix=f"{id(trainer)}.py",
mode="w+",
encoding="utf-8",
dir=USER_CONFIG_DIR / "DDP",
delete=False,
) as file:
file.write(content)
return file.name
@ -53,16 +55,17 @@ if __name__ == "__main__":
def generate_ddp_command(world_size, trainer):
"""Generates and returns command for distributed training."""
import __main__ # noqa local import to avoid https://github.com/Lightning-AI/lightning/issues/15218
if not trainer.resume:
shutil.rmtree(trainer.save_dir) # remove the save_dir
file = generate_ddp_file(trainer)
dist_cmd = 'torch.distributed.run' if TORCH_1_9 else 'torch.distributed.launch'
dist_cmd = "torch.distributed.run" if TORCH_1_9 else "torch.distributed.launch"
port = find_free_network_port()
cmd = [sys.executable, '-m', dist_cmd, '--nproc_per_node', f'{world_size}', '--master_port', f'{port}', file]
cmd = [sys.executable, "-m", dist_cmd, "--nproc_per_node", f"{world_size}", "--master_port", f"{port}", file]
return cmd, file
def ddp_cleanup(trainer, file):
"""Delete temp file if created."""
if f'{id(trainer)}.py' in file: # if temp_file suffix in file
if f"{id(trainer)}.py" in file: # if temp_file suffix in file
os.remove(file)