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.

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

Implement label_errors on OD tasks #100

Draft
wants to merge 6 commits into
base: main
Choose a base branch
from

Conversation

gheorghetutunaru
Copy link
Contributor

No description provided.

@gheorghetutunaru gheorghetutunaru force-pushed the feat/test-od-label-errors branch 14 times, most recently from e3221a5 to c8de677 Compare June 29, 2022 11:36
@gheorghetutunaru gheorghetutunaru force-pushed the feat/test-od-label-errors branch 3 times, most recently from 0526bd5 to 053fa5a Compare June 29, 2022 14:23
@gheorghetutunaru gheorghetutunaru force-pushed the feat/test-od-label-errors branch from 053fa5a to 058f3f0 Compare June 29, 2022 14:29
@@ -8,3 +8,4 @@ kiliautoml/utils/ultralytics/yolov5/artifacts
wandb/**
.mypy_cache/**
kiliautoml.egg-info/**
error_labels.json
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this should land in the code repository by default, so you can rm it.

clear_dataset_cache
and os.path.exists(data_path)
and os.path.isdir(data_path)
and (not label_error_n_folds or (label_error_n_folds and label_error_cv_fold == 0))
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not label_error_n_folds or (label_error_n_folds and label_error_cv_fold == 0) should be put into a variable with an explicit name.

from typing import Dict, List

from typing_extensions import Literal, TypedDict

HOME = os.path.join(os.getenv("HOME"), ".cache", "kili", "automl") # type: ignore

AUTOML_REPO_ROOT = Path(__file__).resolve().parents[2]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not sure that this will work if automl is installed as a package and used from another directory.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

but anyway no big deal since we should get rid of Yolo as submodule moving forward


# Predict by batch of images
pbar = tqdm(dataloader, bar_format="{l_bar}{bar:10}{r_bar}{bar:-10b}") # progress bar
for _, (imgs_batche, targets, paths, shapes) in enumerate(pbar):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

imags_batch

@@ -11,13 +11,14 @@ exclude = '''

[tool.pylint.master]
suggestion-mode = true
ignore-paths = [ "^kiliautoml/utils/ultralytics/yolov5/.*$"]
ignore-paths = [ "^kiliautoml/utils/ultralytics/yolov5/.*$", "kiliautoml/utils/label_errors/yolo_general.py", "kiliautoml/utils/label_errors/yolo_metrics.py"]
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

ignored because this is code we copied from yolo ?


import numpy as np

from commands.prioritize import Prioritizer, PriorityQueue

print(sys.path)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

rm

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants