Skip to content
Snippets Groups Projects
Commit f3e0b8c9 authored by André Anjos's avatar André Anjos :speech_balloon: Committed by Daniel CARRON
Browse files

[doc] Fix docs of generate-saliencymaps

parent 2a7150d6
No related branches found
No related tags found
1 merge request!12Adds grad-cam support on classifiers
...@@ -27,4 +27,4 @@ class ConfigCommand(_BaseConfigCommand): ...@@ -27,4 +27,4 @@ class ConfigCommand(_BaseConfigCommand):
if self.epilog: if self.epilog:
formatter.write_paragraph() formatter.write_paragraph()
for line in self.epilog.split("\n"): for line in self.epilog.split("\n"):
formatter.write_text(line) formatter.write(line + "\n")
...@@ -7,10 +7,11 @@ import typing ...@@ -7,10 +7,11 @@ import typing
import click import click
from clapper.click import ConfigCommand, ResourceOption, verbosity_option from clapper.click import ResourceOption, verbosity_option
from clapper.logging import setup from clapper.logging import setup
from ..models.typing import VisualisationType from ..models.typing import VisualisationType
from .click import ConfigCommand
logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s") logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
...@@ -20,15 +21,13 @@ logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s") ...@@ -20,15 +21,13 @@ logger = setup(__name__.split(".")[0], format="%(levelname)s: %(message)s")
cls=ConfigCommand, cls=ConfigCommand,
epilog="""Examples: epilog="""Examples:
\b 1. Generates saliency maps for all prediction dataloaders on a datamodule,
1. Generates saliency maps for all prediction dataloaders on a datamodule, using a pre-trained DenseNet model, and saves them as numpy-pickeled
using a pre-trained DenseNet model, and saves them as numpy-pickeled objects on the output directory:
objects on the output directory:
.. code:: sh .. code:: sh
\b ptbench generate-saliencymaps -vv densenet tbx11k-v1-healthy-vs-atb --weight=path/to/model_final.pth --output-folder=path/to/visualisations
ptbench generate-saliencymaps -vv densenet tbx11k-v1-healthy-vs-atb --weight=path/to/model_final.pth --output-folder=path/to/visualisations
""", """,
) )
......
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