mrq/DL-Art-School
1
3
Fork 5
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Fix distributed launch for large distributed runs

Browse Source
This commit is contained in:
James Betker 2020-08-25 15:42:59 -06:00
parent 03eb29a4d9
commit 19487d9bbd
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
codes/train.py
View File

@ -32,7 +32,7 @@ def init_dist(backend='nccl', **kwargs):
def main():
#### options
parser = argparse.ArgumentParser()
parser.add_argument('-opt', type=str, help='Path to option YAML file.', default='../options/train_imgset_spsr_switched2_fullimgref.yml')
parser.add_argument('-opt', type=str, help='Path to option YAML file.', default='../options/train_imgset_spsr_switched2_xlbatch_ragan.yml')
parser.add_argument('--launcher', choices=['none', 'pytorch'], default='none',
help='job launcher')
parser.add_argument('--local_rank', type=int, default=0)
@ -121,7 +121,7 @@ def main():
# torch.backends.cudnn.deterministic = True
#### create train and val dataloader
dataset_ratio = 200 # enlarge the size of each epoch
dataset_ratio = 1 # enlarge the size of each epoch
for phase, dataset_opt in opt['datasets'].items():
if phase == 'train':
train_set = create_dataset(dataset_opt)