35 lines
1.0 KiB
Python
35 lines
1.0 KiB
Python
|
# Resume all interrupted trainings in yolov5/ dir including DPP trainings
|
||
|
|
# Usage: $ python utils/aws/resume.py
|
||
|
|
|
||
|
|
import os
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
import torch
|
||
|
|
import yaml
|
||
|
|
|
||
|
|
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)
|