yolov7 / utils /aws /resume.py
akhaliq's picture
akhaliq HF staff
add files
e20a59b
raw
history blame
1.11 kB
# Resume all interrupted trainings in yolor/ dir including DDP trainings
# Usage: $ python utils/aws/resume.py
import os
import sys
from pathlib import Path
import torch
import yaml
sys.path.append('./') # to run '$ python *.py' files in subdirectories
port = 0 # --master_port
path = Path('').resolve()
for last in path.rglob('*/**/last.pt'):
ckpt = torch.load(last)
if ckpt['optimizer'] is None:
continue
# Load opt.yaml
with open(last.parent.parent / 'opt.yaml') as f:
opt = yaml.load(f, Loader=yaml.SafeLoader)
# Get device count
d = opt['device'].split(',') # devices
nd = len(d) # number of devices
ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
if ddp: # multi-GPU
port += 1
cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
else: # single-GPU
cmd = f'python train.py --resume {last}'
cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
print(cmd)
os.system(cmd)