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

Jump to bottom

Fixed bug in COCOPoseEstimationDataset which caused the images or reversed channel order used in predict() #1609

Merged
merged 2 commits into from
Nov 5, 2023
Merged

Fixed bug in COCOPoseEstimationDataset which caused the images or reversed channel order used in predict() #1609

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dd35080
Added missing rgb2bgr conversion
BloodAxe Nov 4, 2023
ee58fd8
Merge branch 'master' into feature/SG-000-fix-preprocessing-params
ofrimasad Nov 5, 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
19 changes: 18 additions & 1 deletion ...uper_gradients/training/datasets/pose_estimation_datasets/coco_pose_estimation_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
from super_gradients.common.decorators.factory_decorator import resolve_param
from super_gradients.common.factories.transforms_factory import TransformsFactory
from super_gradients.common.factories.type_factory import TypeFactory
from super_gradients.common.object_names import Datasets
from super_gradients.common.object_names import Datasets, Processings
from super_gradients.common.registry.registry import register_dataset
from super_gradients.training.datasets.data_formats.bbox_formats.xywh import xywh_to_xyxy, xyxy_to_xywh
from super_gradients.training.datasets.pose_estimation_datasets.abstract_pose_estimation_dataset import AbstractPoseEstimationDataset
Expand Down Expand Up @@ -206,3 +206,20 @@ def _get_crowd_mask(self, anno, img_info) -> np.ndarray:
m += mask

return (m < 0.5).astype(np.float32)

def get_dataset_preprocessing_params(self) -> dict:
"""
This method returns a dictionary of parameters describing preprocessing steps to be applied to the dataset.
:return:
"""
rgb_to_bgr = {Processings.ReverseImageChannels: {}}
image_to_tensor = {Processings.ImagePermute: {"permutation": (2, 0, 1)}}
pipeline = [rgb_to_bgr] + self.transforms.get_equivalent_preprocessing() + [image_to_tensor]
params = dict(
conf=0.05,
image_processor={Processings.ComposeProcessing: {"processings": pipeline}},
edge_links=self.edge_links,
edge_colors=self.edge_colors,
keypoint_colors=self.keypoint_colors,
)
return params