Skip to content
Snippets Groups Projects
Commit ac1f954c authored by Yoann Schneider's avatar Yoann Schneider :tennis: Committed by Mélodie Boillet
Browse files

Document training subcommands

parent ef1e6506
No related branches found
No related tags found
1 merge request!53Document training subcommands
......@@ -7,7 +7,7 @@ from dan.ocr.line.train import run as run_train
def add_generate_parser(subcommands) -> None:
parser = subcommands.add_parser(
"generate",
description=__doc__,
description="Generate synthetic data to train DAN models.",
help="Generate synthetic data to train DAN models.",
)
parser.set_defaults(func=run_generate)
......@@ -16,7 +16,7 @@ def add_generate_parser(subcommands) -> None:
def add_line_parser(subcommands) -> None:
parser = subcommands.add_parser(
"line",
description=__doc__,
description="Train a DAN model at line level.",
help="Train a DAN model at line level.",
)
parser.set_defaults(func=run_train)
......@@ -2,6 +2,14 @@
Use the `teklia-dan train` command to train a new DAN model.
Two subcommands are available depending on your dataset:
`line`
: Train a DAN model at line-level.
`document`
: Train a DAN model at document-level.
## Remarks (for pre-training and training)
All hyperparameters are specified and editable in the training scripts (meaning are in comments).
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment