Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove CenterCrop from Classification test pipeline and editing missing docs link #2375

Merged
merged 2 commits into from
Jul 19, 2023
Merged

Remove CenterCrop from Classification test pipeline and editing missing docs link #2375

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6ff762c
Fix missing link for docs and removing centercrop for classification …
sungmanc Jul 19, 2023
6c44220
Revert the test threshold
sungmanc Jul 19, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/source/guide/explanation/algorithms/segmentation/semantic_segmentation.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ Dataset Format

For the dataset handling inside OpenVINO™ Training Extensions, we use `Dataset Management Framework (Datumaro) <https://github.com/openvinotoolkit/datumaro>`_.

At this end we support `Common Semantic Segmentation <https://openvinotoolkit.github.io/datumaro/docs/formats/common_semantic_segmentation/>`_ data format.
At this end we support `Common Semantic Segmentation <https://github.com/openvinotoolkit/datumaro/blob/develop/docs/source/docs/data-formats/formats/common_semantic_segmentation.md>`_ data format.
If you organized supported dataset format, starting training will be very simple. We just need to pass a path to the root folder and desired model template to start training:

.. code-block::
Expand Down Expand Up @@ -278,4 +278,4 @@ It can be launched only with supervised (incremental) training type.
.. Incremental Learning
.. ********************

.. To be added soon
.. To be added soon
5 changes: 2 additions & 3 deletions src/otx/algorithms/classification/configs/base/data/data_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
__resize_target_size = 224

__train_pipeline = [
dict(type="RandomResizedCrop", size=224, efficientnet_style=True),
dict(type="RandomResizedCrop", size=__resize_target_size, efficientnet_style=True),
dict(type="RandomFlip", flip_prob=0.5, direction="horizontal"),
dict(type="Normalize", **__img_norm_cfg),
dict(type="ImageToTensor", keys=["img"]),
Expand All @@ -29,8 +29,7 @@
]

__test_pipeline = [
dict(type="Resize", size=(256, -1)),
dict(type="CenterCrop", crop_size=224),
dict(type="Resize", size=__resize_target_size),
dict(type="Normalize", **__img_norm_cfg),
dict(type="ImageToTensor", keys=["img"]),
dict(type="Collect", keys=["img"]),
Expand Down
3 changes: 1 addition & 2 deletions tests/e2e/cli/classification/test_classification.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,8 +180,7 @@ def test_otx_explain_openvino(self, template, tmp_dir_path):
@pytest.mark.parametrize("half_precision", [True, False])
def test_otx_eval_openvino(self, template, tmp_dir_path, half_precision):
tmp_dir_path = tmp_dir_path / "multi_class_cls"
# FIXME [Jaeguk] Revert threshold to 0.2 when model api supports resize and centercrop.
otx_eval_openvino_testing(template, tmp_dir_path, otx_dir, args, threshold=0.5, half_precision=half_precision)
otx_eval_openvino_testing(template, tmp_dir_path, otx_dir, args, threshold=0.2, half_precision=half_precision)

@e2e_pytest_component
@pytest.mark.skipif(TT_STABILITY_TESTS, reason="This is TT_STABILITY_TESTS")
Expand Down