We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
I notice that in file "https://github.com/facebookresearch/detectron2/blob/main/detectron2/modeling/backbone/vit.py", in line 471: "size_divisiblity": self._size_divisibility, The key is "size_divisiblity". But in file "https://github.com/facebookresearch/detectron2/blob/main/detectron2/structures/image_list.py", line 96: if "size_divisibility" in padding_constraints: The key is "size_divisibility", which means that the key in "vit.py" is missing one “i”,which leads to different padding foramt for images( one is square and the other is not). I want to know that is this a bug? Or it's just right to pad the image to square in vitdet?
The text was updated successfully, but these errors were encountered:
#4981 deals with this.
Sorry, something went wrong.
No branches or pull requests
I notice that in file "https://github.com/facebookresearch/detectron2/blob/main/detectron2/modeling/backbone/vit.py", in line 471:
"size_divisiblity": self._size_divisibility,
The key is "size_divisiblity".
But in file "https://github.com/facebookresearch/detectron2/blob/main/detectron2/structures/image_list.py", line 96:
if "size_divisibility" in padding_constraints:
The key is "size_divisibility", which means that the key in "vit.py" is missing one “i”,which leads to different padding foramt for images( one is square and the other is not).
I want to know that is this a bug? Or it's just right to pad the image to square in vitdet?
The text was updated successfully, but these errors were encountered: