Examples and tutorials on using SOTA computer vision models and techniques. Learn everything from old-school ResNet, through YOLO and object-detection transformers like DETR, to the latest models like Grounding DINO and SAM.
Pin the ultralytics version to the latest one. This avoids the issue where new albumentations are not supported by ultralytics, but not specified in their requirements files. This would fail during training.
Description
Pin the ultralytics version to the latest one. This avoids the issue where new albumentations are not supported by ultralytics, but not specified in their requirements files. This would fail during training.
Alternatively, the following would work:
ALSO, I've updated and pinned supervision to the latest version.
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Ran notebook.
Any specific deployment considerations
Another change is coming soon, filling in the missing picture in the end.
Docs