-
Notifications
You must be signed in to change notification settings - Fork 7k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
aligned with partial original implementation
- Loading branch information
1 parent
aa95139
commit 1fddecc
Showing
5 changed files
with
280 additions
and
59 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,122 @@ | ||
| import argparse | ||
| import os | ||
| import uuid | ||
| from pathlib import Path | ||
|
|
||
| import train | ||
| import submitit | ||
|
|
||
|
|
||
| def parse_args(): | ||
| train_parser = train.get_args_parser(add_help=False) | ||
| parser = argparse.ArgumentParser("Submitit for train", parents=[train_parser], add_help=True) | ||
| parser.add_argument("--ngpus", default=8, type=int, help="Number of gpus to request on each node") | ||
| parser.add_argument("--nodes", default=1, type=int, help="Number of nodes to request") | ||
| parser.add_argument("--timeout", default=60*24*30, type=int, help="Duration of the job") | ||
| parser.add_argument("--job_dir", default="", type=str, help="Job dir. Leave empty for automatic.") | ||
| parser.add_argument("--partition", default="train", type=str, help="the partition (default train).") | ||
| return parser.parse_args() | ||
|
|
||
|
|
||
| def get_shared_folder() -> Path: | ||
| user = os.getenv("USER") | ||
| path = "/data/checkpoints" | ||
| if Path(path).is_dir(): | ||
| p = Path(f"{path}/{user}/experiments") | ||
| p.mkdir(exist_ok=True) | ||
| return p | ||
| raise RuntimeError("No shared folder available") | ||
|
|
||
|
|
||
| def get_init_file_folder() -> Path: | ||
| user = os.getenv("USER") | ||
| path = "/shared" | ||
| if Path(path).is_dir(): | ||
| p = Path(f"{path}/{user}") | ||
| p.mkdir(exist_ok=True) | ||
| return p | ||
| raise RuntimeError("No shared folder available") | ||
|
|
||
|
|
||
| def get_init_file(): | ||
| # Init file must not exist, but it's parent dir must exist. | ||
| os.makedirs(str(get_init_file_folder()), exist_ok=True) | ||
| init_file = get_init_file_folder() / f"{uuid.uuid4().hex}_init" | ||
| if init_file.exists(): | ||
| os.remove(str(init_file)) | ||
| return init_file | ||
|
|
||
|
|
||
| class Trainer(object): | ||
| def __init__(self, args): | ||
| self.args = args | ||
|
|
||
| def __call__(self): | ||
| import train | ||
|
|
||
| self._setup_gpu_args() | ||
| train.main(self.args) | ||
|
|
||
| def checkpoint(self): | ||
| import os | ||
| import submitit | ||
| from pathlib import Path | ||
|
|
||
| self.args.dist_url = get_init_file().as_uri() | ||
| checkpoint_file = os.path.join(self.args.output_dir, "checkpoint.pth") | ||
| if os.path.exists(checkpoint_file): | ||
| self.args.resume = checkpoint_file | ||
| print("Requeuing ", self.args) | ||
| empty_trainer = type(self)(self.args) | ||
| return submitit.helpers.DelayedSubmission(empty_trainer) | ||
|
|
||
| def _setup_gpu_args(self): | ||
| import submitit | ||
| from pathlib import Path | ||
|
|
||
| job_env = submitit.JobEnvironment() | ||
| self.args.output_dir = Path(str(self.args.output_dir).replace("%j", str(job_env.job_id))) | ||
| self.args.gpu = job_env.local_rank | ||
| self.args.rank = job_env.global_rank | ||
| self.args.world_size = job_env.num_tasks | ||
| print(f"Process group: {job_env.num_tasks} tasks, rank: {job_env.global_rank}") | ||
|
|
||
|
|
||
| def main(): | ||
| args = parse_args() | ||
| if args.job_dir == "": | ||
| args.job_dir = get_shared_folder() / "%j" | ||
|
|
||
| # Note that the folder will depend on the job_id, to easily track experiments | ||
| executor = submitit.AutoExecutor(folder=args.job_dir, slurm_max_num_timeout=300) | ||
|
|
||
| # cluster setup is defined by environment variables | ||
| num_gpus_per_node = args.ngpus | ||
| nodes = args.nodes | ||
| timeout_min = args.timeout | ||
|
|
||
| executor.update_parameters( | ||
| #mem_gb=96 * num_gpus_per_node, # 768GB per machine | ||
| gpus_per_node=num_gpus_per_node, | ||
| tasks_per_node=num_gpus_per_node, # one task per GPU | ||
| cpus_per_task=12, # 96 cpus per machine | ||
| nodes=nodes, | ||
| timeout_min=timeout_min, # max is 60 * 72 | ||
| slurm_partition=args.partition, | ||
| slurm_signal_delay_s=120, | ||
| ) | ||
|
|
||
|
|
||
| executor.update_parameters(name="torchvision") | ||
|
|
||
| args.dist_url = get_init_file().as_uri() | ||
| args.output_dir = args.job_dir | ||
|
|
||
| trainer = Trainer(args) | ||
| job = executor.submit(trainer) | ||
|
|
||
| print("Submitted job_id:", job.job_id) | ||
|
|
||
|
|
||
| if __name__ == "__main__": | ||
| main() |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.