Updated device selection string with fallback for non-git directories.
```python
def select_device(device='', batch_size=None):
    # device = 'cpu' or '0' or '0,1,2,3'
    s = f'YOLOv5 🚀 {git_describe() or date_modified()} torch {torch.__version__} '  # string
...
```

* PyTorch Hub models default to CUDA:0 if available

* device as string bug fix

* Integer printout

* test.py 'Labels'

* Update train.py

Signed-off-by: xiaowo1996 <429740343@qq.com>

* Add colorful()

* update

* newline fix

* add git description

* --always

* update loss scaling

* update loss scaling 2

* rename to colorstr()

* Update C3 module

* Update C3 module

* Update C3 module

* Update C3 module

* update

* update

* update

* update

* update

* update

* update

* update

* update

* updates

* updates

* updates

* updates

* updates

* updates

* updates

* updates

* updates

* updates

* update

* update

* update

* update

* updates

* updates

* updates

* updates

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update datasets

* update

* update

* update

* update attempt_downlaod()

* merge

* merge

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* parameterize eps

* comments

* gs-multiple

* update

* max_nms implemented

* Create one_cycle() function

* update

* update

* update

* update

* update

* update

* update

* update study.png

* update study.png

* Update datasets.py

* torch.cuda.synchronize() update

* torch.cuda.synchronize() update

* torch.cuda.synchronize() update

* newline

* Display correct CUDA devices

* cleanup

FLOPS to GFLOPS

* Fix torch GPU error

* Update torch_utils.py

single-line device =

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

* 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.