Add segmentation + object detection image processors #20160
amyeroberts
marked this pull request as ready for review 3 years ago
Add transforms for object detection
f1b51737
DETR models + Yolos
e25039b8
Scrappy additions
d3eb2c18
Maskformer image processor
97d3dfd8
Fix up; MaskFormer tests
46c86207
Update owlvit processor
4e6dc4fd
Add to docs
81b3a8b9
OwlViT tests
6876de85
Update pad logic
937b2811
Remove changes to transforms
a7b6df2d
Import fn directly
c6f8c9d2
Update to include pad transformation
d75a6fb7
Remove uninstended changes
ecb34a75
Add new owlvit post processing function
2cc5ac39
Tidy up
e3d0710a
Fix copies
91a9bcc7
Fix some copies
caf78cc9
Include device fix
c8e10895
Fix scipy imports
9fde9853
Update _pad_image
31aca4c9
Update padding functionality
5909cc37
Fix bug
e6735199
Properly handle ignore index
f3064de2
Fix up
1217f85b
Remove defaults to None in docstrings
59b3a722
Fix docstrings & docs
9bc7d916
Fix sizes bug
06bd412e
Resolve conflicts in init
4d84ca65
Cast to float after resizing
271e82b4
Tidy & add size if missing
8b40a893
Allow kwards when processing for owlvit
66cff404
sgugger
approved these changes
on 2022-11-29
Update test values
4979808c
amyeroberts
deleted the add-image-processor-detr branch 3 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub