mirrors/mmsegmentation
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmsegmentation.git synced 2025-06-03 22:03:48 +08:00
Code Issues Projects Releases Wiki Activity

Add load-from flag (#33)

Browse Source 
* Add load-from flag

* minor update

Co-authored-by: Jiarui XU <xvjiarui0826@gmail.com>
This commit is contained in:
Evgeny Nizhibitsky 2020-08-06 16:17:49 +03:00 committed by GitHub
parent 2b801dedfc
commit 00f56eb00f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
docs/getting_started.md
View File

@ -241,11 +241,12 @@ Optional arguments are:
- `--no-validate` (**not suggested**): By default, the codebase will perform evaluation at every k iterations during the training. To disable this behavior, use `--no-validate`. - `--no-validate` (**not suggested**): By default, the codebase will perform evaluation at every k iterations during the training. To disable this behavior, use `--no-validate`.
- `--work-dir ${WORK_DIR}`: Override the working directory specified in the config file. - `--work-dir ${WORK_DIR}`: Override the working directory specified in the config file.
- `--resume-from ${CHECKPOINT_FILE}`: Resume from a previous checkpoint file. - `--resume-from ${CHECKPOINT_FILE}`: Resume from a previous checkpoint file (to continue the training process).
- `--load-from ${CHECKPOINT_FILE}`: Load weights from a checkpoint file (to start finetuning for another task).
Difference between `resume-from` and `load-from`: Difference between `resume-from` and `load-from`:
`resume-from` loads both the model weights and optimizer status, and the iteration number is also inherited from the specified checkpoint. It is usually used for resuming the training process that is interrupted accidentally. - `resume-from` loads both the model weights and optimizer state including the iteration number.
`load-from` only loads the model weights and the training iteration starts from 0. It is usually used for finetuning. - `load-from` loads only the model weights, starts the training from iteration 0.
### Train with multiple machines ### Train with multiple machines

4
tools/train.py
View File

@ -20,6 +20,8 @@ def parse_args():
parser = argparse.ArgumentParser(description='Train a segmentor') parser = argparse.ArgumentParser(description='Train a segmentor')
parser.add_argument('config', help='train config file path') parser.add_argument('config', help='train config file path')
parser.add_argument('--work_dir', help='the dir to save logs and models') parser.add_argument('--work_dir', help='the dir to save logs and models')
parser.add_argument(
'--load-from', help='the checkpoint file to load weights from')
parser.add_argument( parser.add_argument(
'--resume-from', help='the checkpoint file to resume from') '--resume-from', help='the checkpoint file to resume from')
parser.add_argument( parser.add_argument(
@ -76,6 +78,8 @@ def main():
# use config filename as default work_dir if cfg.work_dir is None # use config filename as default work_dir if cfg.work_dir is None
cfg.work_dir = osp.join('./work_dirs', cfg.work_dir = osp.join('./work_dirs',
osp.splitext(osp.basename(args.config))[0]) osp.splitext(osp.basename(args.config))[0])
if args.load_from is not None:
cfg.load_from = args.load_from
if args.resume_from is not None: if args.resume_from is not None:
cfg.resume_from = args.resume_from cfg.resume_from = args.resume_from
if args.gpu_ids is not None: if args.gpu_ids is not None: