-
Notifications
You must be signed in to change notification settings - Fork 7k
Issues: pytorch/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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Batching tv_tensors.Image tensors does not preserve tv_tensors.Image type
#9039
opened Apr 25, 2025 by
Balocre
Setting a list of no transforms to
transforms
argument of RandomApply()
gets the indirect error message
#9022
opened Apr 18, 2025 by
hyperkai
AttributeError: module 'torch.library' has no attribute 'register_fake'
#9020
opened Apr 16, 2025 by
WangXinYi111
torchvision 0.21.0+cu126 RuntimeError: operator torchvision::nms does not exist
#8985
opened Mar 19, 2025 by
AndrewTsao
Failed to install vision based on python 3.13t(free-threaded) on Windows OS
#8967
opened Mar 13, 2025 by
jameszhouyi
The explanation for
all_ops
parameter of AugMix()
is not clear enough.
#8957
opened Mar 7, 2025 by
hyperkai
Setting a float value to
magnitude
argument of RandAugment()
gets the wrong error message
#8941
opened Feb 25, 2025 by
hyperkai
Torchvision Faster R-CNN onnx export with dynamic batch size fails during inference
#8937
opened Feb 25, 2025 by
davidgill97
[free threading] Support for free threading Python in torchvision
#8916
opened Feb 18, 2025 by
atalman
Setting
0
and 1
to p
argument of RandomAutocontrast()
gets the same results
#8915
opened Feb 18, 2025 by
hyperkai
Setting
-5
and 5
to sharpness_factor
argument of RandomAdjustSharpness()
sharpens and blurs images respectively
#8911
opened Feb 18, 2025 by
hyperkai
For
kernel_size
parameter, the doc of GaussianBlur()
doesn't explain which is width or height
#8907
opened Feb 15, 2025 by
hyperkai
Batched NMS generates onnx IF operator, which causes onnx conversion problem
#8892
opened Jan 31, 2025 by
RiverLight4
Previous Next
ProTip!
Follow long discussions with comments:>50.