* Profile() feature addition

* cleanup

* Update torch_utils.py

fix issue#113 , inputs device should be same with model parameters' device

* Update torch_utils.py

* Update torch_utils.py

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

* 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

* torch 1.7.0 compatibility updates

* add inference verification

* the value should be a list to unpacking

* filter the None labels

* update readme to remove apex dependency

* add support for DWConv fuse operation

* 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>

* Single-source training

* Extract hyperparameters into seperate files

* weight decay scientific notation yaml reader bug fix

* remove import glob

* intersect_dicts() implementation

* 'or' bug fix

* .to(device) bug fix

* PyTorch have Automatic Mixed Precision (AMP) Training.

* Fixed the problem of inconsistent code length indentation

* Fixed the problem of inconsistent code length indentation

* Mixed precision training is turned on by default

* update yolo.py TTA flexibility and extensibility

* Update scale_img()

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

I submitted it once in your yolov3 project, you seem to accept it? I'm not sure. I'll submit PR again.