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

[Fix] Fix mmseg.api.inference inference_segmentor #1849

Merged
merged 5 commits into from
Sep 13, 2022
Merged

[Fix] Fix mmseg.api.inference inference_segmentor #1849

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
40c8fb0
[Fix] Fix mmseg.api.inference inference_segmentor
jinwonkim93 Aug 1, 2022
1cf6564
fix typo
jinwonkim93 Aug 1, 2022
2f6c08a
Update mmseg/apis/inference.py
jinwonkim93 Aug 12, 2022
b41af6a
Merge branch 'open-mmlab:master' into fix_segmentor_inference
jinwonkim93 Aug 12, 2022
82182c4
Merge branch 'open-mmlab:master' into fix_segmentor_inference
jinwonkim93 Sep 6, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
Prev Previous commit
Next Next commit
Update mmseg/apis/inference.py 
Co-authored-by: Hakjin Lee <[email protected]>
  • Loading branch information
@jinwonkim93 @nijkah
jinwonkim93 and nijkah committed Aug 12, 2022
commit 2f6c08a811824c00d4f66225b563c0592f2ec7c2
18 changes: 7 additions & 11 deletions mmseg/apis/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,17 +84,13 @@ def inference_segmentor(model, imgs):
test_pipeline = [LoadImage()] + cfg.data.test.pipeline[1:]
test_pipeline = Compose(test_pipeline)
# prepare data
if isinstance(imgs, list):
data = []
for img in imgs:
img_data = dict(img=img)
img_data = test_pipeline(img_data)
data.append(img_data)
data = collate(data, samples_per_gpu=len(imgs))
else:
data = dict(img=imgs)
data = test_pipeline(data)
data = collate([data], samples_per_gpu=1)
data = []
imgs = imgs if isinstance(imgs, list) else [imgs]
for img in imgs:
img_data = dict(img=img)
img_data = test_pipeline(img_data)
data.append(img_data)
data = collate(data, samples_per_gpu=len(imgs))
if next(model.parameters()).is_cuda:
# scatter to specified GPU
data = scatter(data, [device])[0]
Expand Down