Skip to content

Lifelong learning supporting non-structure #352

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Lifelong learning supporting non-structure #352

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
98a4047
Add lifelong learning example: semantic segmentation
luosiqi Aug 12, 2022
e5d2291
Sedna integrates unstructured data in lib
luosiqi Aug 12, 2022
53e5ae4
Merge pull request #349 from luosiqi/dev-lifelong-n
kubeedge-bot Aug 12, 2022
88827ef
Code check and base model improvement
luosiqi Aug 17, 2022
3ed85a0
Merge pull request #350 from luosiqi/dev-lifelong-n
kubeedge-bot Aug 19, 2022
572f4e3
Add pylint in ci
Sep 8, 2022
e12ccac
Merge pull request #361 from JimmyYang20/lifelong-ci
kubeedge-bot Sep 8, 2022
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
38 changes: 38 additions & 0 deletions examples/lifelong_learning/RFNet/accuracy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,38 @@
from basemodel import val_args
Copy link
Contributor

@JoeyHwong-gk JoeyHwong-gk Aug 22, 2022

Choose a reason for hiding this comment

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

The import of the relative path should be adjusted.

from utils.metrics import Evaluator
from tqdm import tqdm
from dataloaders import make_data_loader
from sedna.common.class_factory import ClassType, ClassFactory
Copy link
Contributor

@JoeyHwong-gk JoeyHwong-gk Aug 22, 2022

Choose a reason for hiding this comment

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

note the order of import


__all__ = ('accuracy')

@ClassFactory.register(ClassType.GENERAL)
def accuracy(y_true, y_pred, **kwargs):
Copy link
Contributor

@JoeyHwong-gk JoeyHwong-gk Aug 22, 2022

Choose a reason for hiding this comment

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

Common keyword. Use alias while register.

args = val_args()
_, _, test_loader, num_class = make_data_loader(args, test_data=y_true)
evaluator = Evaluator(num_class)

tbar = tqdm(test_loader, desc='\r')
Copy link
Contributor

@JoeyHwong-gk JoeyHwong-gk Aug 22, 2022

Choose a reason for hiding this comment

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

useless

for i, (sample, img_path) in enumerate(tbar):
if args.depth:
image, depth, target = sample['image'], sample['depth'], sample['label']
else:
image, target = sample['image'], sample['label']
if args.cuda:
image, target = image.cuda(), target.cuda()
if args.depth:
depth = depth.cuda()
Copy link
Contributor

@JoeyHwong-gk JoeyHwong-gk Aug 22, 2022

Choose a reason for hiding this comment

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

Check whether the device supports GPU.


target[target > evaluator.num_class-1] = 255
target = target.cpu().numpy()
# Add batch sample into evaluator
evaluator.add_batch(target, y_pred[i])

# Test during the training
# Acc = evaluator.Pixel_Accuracy()
CPA = evaluator.Pixel_Accuracy_Class()
mIoU = evaluator.Mean_Intersection_over_Union()
FWIoU = evaluator.Frequency_Weighted_Intersection_over_Union()

print("CPA:{}, mIoU:{}, fwIoU: {}".format(CPA, mIoU, FWIoU))
return CPA
Loading