Skip to content

/ vision

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

341 Open 1,020 Closed
341 Open 1,020 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
Is paste_masks_in_image fixed?
#3199 opened Dec 22, 2020 by nickponline
Boxes with negative scores in NMS input?
#3198 opened Dec 21, 2020 by masahi
Cannot Build With FFmpeg Support question topic: build topic: video
#3188 opened Dec 18, 2020 by KumaTea
Are these 2 lines of code necessary? question
#3184 opened Dec 17, 2020 by jc-hou
1
CI Conda builds broken on Linux module: ci
#3183 opened Dec 17, 2020 by datumbox
2
Colab model demo notebooks output is not human-readable, just a numeric tensor topic: classification
#3176 opened Dec 16, 2020 by Tylersuard
4
Vectorize the equalize transformation enhancement module: transforms
#3173 opened Dec 14, 2020 by datumbox
2
Getting Error: NotADirectoryError: [WinError 267] The directory name is invalid. File and folder both are valid
#3168 opened Dec 13, 2020 by manojrustagi79
Review naming conventions in io.image *_cpu methods module: io module: ops needs discussion
#3162 opened Dec 12, 2020 by datumbox
Restructure and clean up the video/video_reader C++ implementations module: io
#3155 opened Dec 10, 2020 by datumbox 0 of 6
2
Small discrepancy in accuracy & Some results of pretrained classifiers are missing in doc module: documentation module: models
#3152 opened Dec 10, 2020 by yoshitomo-matsubara
2
Re-enable codecov to run with CircleCI module: ci
#3138 opened Dec 8, 2020 by fmassa
Ability to set canonical scale and level in MultiScaleRoIAlign module: ops topic: object detection
#3129 opened Dec 7, 2020 by baldassarreFe
2
torch.cuda.amp issue with torchvision densenet121 when memory_efficient=True module: models
#3122 opened Dec 4, 2020 by andwurl
2
Why get_num_threads() and set_num_threads(1) in engine.py? Is it essential? module: reference scripts topic: object detection
#3115 opened Dec 4, 2020 by BCMoo
1
_rgb2hsv has an unmentioned requirement of non-negative inputs
#3110 opened Dec 3, 2020 by behxyz
1
5
about retrain shufflenetv2 question question
#3090 opened Dec 2, 2020 by WZMIAOMIAO
Windows C++ library build issues module: c++ frontend windows
#3086 opened Dec 2, 2020 by willyd
1
Getting an error when modifying the faster_rcnn model to add inception_v3 backbone model question
#3083 opened Dec 1, 2020 by lazySperm
test_write_video_with_audio is disabled on Windows module: io module: tests windows
#3078 opened Dec 1, 2020 by fmassa
Clean up the documentation of transforms enhancement good first issue module: documentation
#3071 opened Dec 1, 2020 by datumbox
6
Investigate inconsistent casting inside functional_tensor.py enhancement good first issue module: transforms
#3067 opened Nov 30, 2020 by datumbox
2
Avoid calling torch.rand in Transformation.forward() enhancement good first issue module: transforms needs discussion
#3066 opened Nov 30, 2020 by datumbox
1
Fix DeformConv2d's autocast test flakiness enhancement module: ops module: tests
#3060 opened Nov 30, 2020 by datumbox
How to solve this error? RuntimeError: Could not run 'torchvision::nms' with arguments from the 'CUDA' backend module: ops needs reproduction
#3058 opened Nov 30, 2020 by manmani3
1
ProTip! Find all open issues with in progress development work with linked:pr.
You can’t perform that action at this time.