* Update test.py for IoU in native image-space

* remove redundant

* gn to device

* remove output scale_coords

* --img-size correction

* update

* native-space labels

* pred to predn

* remove clip_coords()

* PyTorch Hub and autoShape update

* comment x for imgs

* reduce comment

* Improved FLOPS computation

* update comment

* Utils reorganization

* Add new utils files

* cleanup

* simplify

* reduce datasets.py

* remove evolve.sh

* loadWebcam cleanup

* Create flatten_recursive() helper function

* cleanup

* print torch version

* autoshape update for PIL greyscale inputs

* autoshape update for PIL greyscale inputs

* torch 1.7.0 compatibility updates

* add inference verification

img size checks are warnings rather than errors, so current implementation allows improperly formed model inputs.

* Update ci-testing.yml

* Update yolo.py

* Update ci-testing.yml

* Update export.py

* Update yolo.py

* initial commit

* remove yolov3-spp from test.py study

* update study --img range

* update mAP

* cleanup and speed updates

* update README plot

* Add logging setup

* Fix fusing layers message

* Fix logging does not have end

* Add logging

* Change logging to use logger

* Update yolo.py

I tried this in a cloned branch, and everything seems to work fine

* Update yolo.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Change print to logging

* Clean function set_logging

* Add line spacing

* Change leftover prints to log

* Fix scanning labels output

* Fix rank naming

* Change leftover print to logging

* Reorganized DDP variables

* Fix type error

* Make quotes consistent

* Fix spelling

* Clean function call

* Add line spacing

* Update datasets.py

* Update train.py

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* expand imports

* optimize

* miss

* fix

* update yolo.py TTA flexibility and extensibility

* Update scale_img()

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>