[go: nahoru, domu]
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

Dev #49

Merged
merged 26 commits into from
May 7, 2018
Merged

Dev #49

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
26 commits
Select commit Hold shift + click to select a range
6580838
*prepare_masks for multiclass problem
apyskir Apr 27, 2018
3fce6b3
fix
apyskir Apr 27, 2018
d8c7acb
list -> tuple
apyskir Apr 30, 2018
ee8c599
evaluate in chunks using COCOeval
taraspiotr Apr 30, 2018
a7d639b
debugging COCOeval
Apr 30, 2018
860a12f
use tempfile in _evaluate_in_chunks
taraspiotr May 1, 2018
3b9f4f9
debug _evaluate_in_chunks
May 1, 2018
aedee00
reorganize _evaluate_in_chunks
taraspiotr May 1, 2018
ae37d49
remove tempfile in _evaluate_in_chunks
May 1, 2018
bae7439
reverse some temp changes
taraspiotr May 1, 2018
dc91594
typo
taraspiotr May 1, 2018
0bb8462
remove redundant file cocoeval.py
taraspiotr May 1, 2018
87c1b57
fix
May 1, 2018
99b0d44
fix
taraspiotr May 1, 2018
c2f67f6
update after review
May 2, 2018
f3668aa
moved generate_prediction to main.py
May 2, 2018
0c06a11
Merge pull request #40 from taraspiotr/dev
jakubczakon May 2, 2018
a0c389e
fix
apyskir May 4, 2018
4e86873
Merge pull request #34 from apyskir/dev-multiclass-gt
jakubczakon May 4, 2018
3664560
fix target image size
apyskir May 4, 2018
c8df308
Merge pull request #41 from apyskir/dev
jakubczakon May 4, 2018
eb3658a
added index notebook
May 4, 2018
27b11d9
Merge pull request #43 from minerva-ml/dev-add_index_notebook
jakubczakon May 4, 2018
94e1903
Merge branch 'master' into dev
May 4, 2018
9d3dbe7
dropped building labeler
May 4, 2018
d9d51a1
Merge pull request #45 from minerva-ml/dev-pipeline_cleanup
jakubczakon May 7, 2018
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
Prev Previous commit
Next Next commit
fix
  • Loading branch information
@taraspiotr
taraspiotr committed May 1, 2018
commit 99b0d44cbd68261dde5f39793a6a4d8200e704de
2 changes: 1 addition & 1 deletion main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,7 +74,7 @@ def _train(pipeline_name, dev_mode):
meta = pd.read_csv(os.path.join(params.meta_dir, 'stage{}_metadata.csv'.format(params.competition_stage)),
low_memory=False)
meta_train = meta[meta['is_train'] == 1]
meta_valid = meta[meta['is_train'] == 1]
meta_valid = meta[meta['is_valid'] == 1]

if dev_mode:
meta_train = meta_train.sample(20, random_state=1234)
Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,11 @@ pandas==0.22.0
imageio==2.2.0
pydot_ng==1.0.0
opencv_python==3.4.0.12
torch==0.2.0.post3
attrdict==2.0.0
scipy==1.0.0
scikit_image==0.13.1
torchvision==0.2.0
torch==0.2.0
numpy==1.14.0
imgaug==0.2.5
neptune_cli==2.8.0
Expand Down
4 changes: 0 additions & 4 deletions utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
from tqdm import tqdm
import tempfile


def read_yaml(filepath):
Expand Down Expand Up @@ -91,7 +90,6 @@ def create_submission(meta, predictions, logger, category_ids, save=False, exper
:return: submission if save==False else True
'''
annotations = []
annotations_counter = 1
logger.info('Creating submission')
for image_id, prediction in zip(meta["ImageId"].values, predictions):
score = 1.0
Expand All @@ -100,15 +98,13 @@ def create_submission(meta, predictions, logger, category_ids, save=False, exper
masks = decompose(category_instances)
for mask_nr, mask in enumerate(masks):
annotation = {}
annotation["id"] = annotations_counter
annotation["image_id"] = int(image_id)
annotation["category_id"] = category_ids[category_nr]
annotation["score"] = score
annotation["segmentation"] = rle_from_binary(mask.astype('uint8'))
annotation['segmentation']['counts'] = annotation['segmentation']['counts'].decode("UTF-8")
annotation["bbox"] = bounding_box_from_rle(rle_from_binary(mask.astype('uint8')))
annotations.append(annotation)
annotations_counter += 1
if save:
submission_filepath = os.path.join(experiment_dir, 'submission.json')
with open(submission_filepath, "w") as fp:
Expand Down