Spaces:
Running
on
Zero
Running
on
Zero
File size: 3,854 Bytes
2ada650 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 |
"""
Copyright (c) 2022, salesforce.com, inc.
All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
For full license text, see the LICENSE_Lavis file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
import datetime
import functools
import os
import torch
import torch.distributed as dist
import timm.models.hub as timm_hub
def setup_for_distributed(is_master):
"""
This function disables printing when not in master process
"""
import builtins as __builtin__
builtin_print = __builtin__.print
def print(*args, **kwargs):
force = kwargs.pop("force", False)
if is_master or force:
builtin_print(*args, **kwargs)
__builtin__.print = print
def is_dist_avail_and_initialized():
if not dist.is_available():
return False
if not dist.is_initialized():
return False
return True
def get_world_size():
if not is_dist_avail_and_initialized():
return 1
return dist.get_world_size()
def get_rank():
if not is_dist_avail_and_initialized():
return 0
return dist.get_rank()
def is_main_process():
return get_rank() == 0
def init_distributed_mode(args):
if args.distributed is False:
print("Not using distributed mode")
args.rank = 0
return
if 'LOCAL_RANK' not in os.environ:
os.environ['LOCAL_RANK'] = str(args.local_rank)
if "RANK" in os.environ and "WORLD_SIZE" in os.environ:
args.rank = int(os.environ["RANK"])
args.world_size = int(os.environ["WORLD_SIZE"])
args.gpu = int(os.environ["LOCAL_RANK"])
elif "SLURM_PROCID" in os.environ:
args.rank = int(os.environ["SLURM_PROCID"])
args.gpu = args.rank % torch.cuda.device_count()
else:
print("Not using distributed mode")
args.distributed = False
args.rank = 0
return
args.distributed = True
torch.cuda.set_device(args.gpu)
args.dist_backend = "nccl"
print(
"| distributed init (rank {}, world {}): {}".format(
args.rank, args.world_size, args.dist_url
),
flush=True,
)
torch.distributed.init_process_group(
backend=args.dist_backend,
init_method=args.dist_url,
world_size=args.world_size,
rank=args.rank,
timeout=datetime.timedelta(
days=365
), # allow auto-downloading and de-compressing
)
torch.distributed.barrier()
setup_for_distributed(args.rank == 0)
def get_dist_info():
if torch.__version__ < "1.0":
initialized = dist._initialized
else:
initialized = dist.is_initialized()
if initialized:
rank = dist.get_rank()
world_size = dist.get_world_size()
else: # non-distributed training
rank = 0
world_size = 1
return rank, world_size
def main_process(func):
@functools.wraps(func)
def wrapper(*args, **kwargs):
rank, _ = get_dist_info()
if rank == 0:
return func(*args, **kwargs)
return wrapper
def download_cached_file(url, check_hash=True, progress=False):
"""
Download a file from a URL and cache it locally. If the file already exists, it is not downloaded again.
If distributed, only the main process downloads the file, and the other processes wait for the file to be downloaded.
"""
def get_cached_file_path():
# a hack to sync the file path across processes
parts = torch.hub.urlparse(url)
filename = os.path.basename(parts.path)
cached_file = os.path.join(timm_hub.get_cache_dir(), filename)
return cached_file
if is_main_process():
timm_hub.download_cached_file(url, check_hash, progress)
if is_dist_avail_and_initialized():
dist.barrier()
return get_cached_file_path()
|