xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-24 06:07:03 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Resolve python argparse DDP bug (#6009)

Browse Source
This commit is contained in:
Glenn Jocher 2023-10-29 20:26:51 +01:00 committed by GitHub
parent 9e424700a8
commit ab0b47e386
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
ultralytics/utils/dist.py
View File

@ -1,12 +1,10 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license # Ultralytics YOLO 🚀, AGPL-3.0 license
import os import os
import re
import shutil import shutil
import socket import socket
import sys import sys
import tempfile import tempfile
from pathlib import Path
from . import USER_CONFIG_DIR from . import USER_CONFIG_DIR
from .torch_utils import TORCH_1_9 from .torch_utils import TORCH_1_9
@ -28,14 +26,19 @@ def generate_ddp_file(trainer):
"""Generates a DDP file and returns its file name.""" """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'''overrides = {vars(trainer.args)} \nif __name__ == "__main__": content = f"""
# Ultralytics Multi-GPU training temp file (should be automatically deleted after use)
overrides = {vars(trainer.args)}
if __name__ == "__main__":
from {module} import {name} from {module} import {name}
from ultralytics.utils import DEFAULT_CFG_DICT from ultralytics.utils import DEFAULT_CFG_DICT
cfg = DEFAULT_CFG_DICT.copy() cfg = DEFAULT_CFG_DICT.copy()
cfg.update(save_dir='') # handle the extra key 'save_dir' cfg.update(save_dir='') # handle the extra key 'save_dir'
trainer = {name}(cfg=cfg, overrides=overrides) trainer = {name}(cfg=cfg, overrides=overrides)
trainer.train()''' results = trainer.train()
"""
(USER_CONFIG_DIR / 'DDP').mkdir(exist_ok=True) (USER_CONFIG_DIR / 'DDP').mkdir(exist_ok=True)
with tempfile.NamedTemporaryFile(prefix='_temp_', with tempfile.NamedTemporaryFile(prefix='_temp_',
suffix=f'{id(trainer)}.py', suffix=f'{id(trainer)}.py',
@ -52,10 +55,7 @@ def generate_ddp_command(world_size, trainer):
import __main__ # noqa local import to avoid https://github.com/Lightning-AI/lightning/issues/15218 import __main__ # noqa local import to avoid https://github.com/Lightning-AI/lightning/issues/15218
if not trainer.resume: if not trainer.resume:
shutil.rmtree(trainer.save_dir) # remove the save_dir shutil.rmtree(trainer.save_dir) # remove the save_dir
file = str(Path(sys.argv[0]).resolve()) file = generate_ddp_file(trainer)
safe_pattern = re.compile(r'^[a-zA-Z0-9_. /\\-]{1,128}$') # allowed characters and maximum of 100 characters
if not (safe_pattern.match(file) and Path(file).exists() and file.endswith('.py')): # using CLI
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() 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]