* VisDrone Dataset Auto-Download

* add visdrone.yaml

* cleanup

* add VisDrone2019-DET-test-dev

* cleanup VOC

* don't resize up in load_image if augmenting

* cleanup

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

* Implement yaml.safe_load()

* yaml.safe_dump()

* Update detect.py

* Update detect.py

* Update greetings.yml

* Update cropping

* cleanup

* Update increment_path()

* Update common.py

* Update detect.py

* Update detect.py

* Update detect.py

* Update common.py

* cleanup

* Update detect.py

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

* PyTorch Hub cv2 .save() .show() bug fix

cv2.rectangle() was failing on non-contiguous np array inputs. This checks for contiguous arrays and applies is necessary:
```python
imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
```

* Update plots.py

```python
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to plot_on_box() input image.'
```

* Update hubconf.py

Expand CI tests to OpenCV image.

* ONNX Simplifier

Add ONNX Simplifier to ONNX export pipeline in export.py. Will auto-install onnx-simplifier if onnx is installed but onnx-simplifier is not.

* Update general.py

* add files

* Update README.md

* Update README.md

* Update restapi.py

pretrained=True and model.eval() are used by default when loading a model now, so no need to call them manually.

* PEP8 reformat

* PEP8 reformat

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

* torch.jit.trace(model, img, strict=False)

* Update check_file()

* Update hubconf.py

* Update README.md

* Youtube livestream detection

* dependancy update to auto install pafy

* Remove print

* include youtube_dl in deps

* PEP8 reformat

* youtube url check fix

* reduce lines

* add comment

* update check_requirements

* stream framerate fix

* Update README.md

* cleanup

* PEP8

* remove cap.retrieve() failure code

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

* wandb_logging PEP8 reformat

* Update wandb_utils.py

* Set resume flag to false

* Check existance of val dataset

* Add label smoothing option

* Correct data type

* add_log

* Remove log

* Add log

* Update loss.py

remove comment (too versbose)

Co-authored-by: phattran <phat.tranhoang@cyberlogitec.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

* Speed profiling improvements

* Update torch_utils.py

deepcopy() required to avoid adding elements to model.

* Update torch_utils.py

When using tqdm, sometimes it can't print in one line and roll to next line.

Add stderr=subprocess.STDOUT to catch error messages.

* W&B resume ddp from run link fix

* Native DDP W&B support for training, resuming

Catch 'fatal: not a git repository' returns and return '' instead (observed in GCP Hub checks).

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
...
```

Co-authored-by: Max Uppenkamp <max.uppenkamp@inform-software.com>

Improved user-feedback following requirements auto-update.

Prints 'Please restart runtime or rerun command for update to take effect.' following package auto-install to inform users to restart/rerun.

* Update check_requirements() with auto-install

This PR builds on an idea I had to automatically install missing dependencies rather than simply report an error message. 

YOLOv5 should now 1) display all dependency issues and not simply display the first missing dependency, and 2) attempt to install/update each missing/VersionConflict package.

* cleanup

* cleanup 2

* Check requirements.txt file exists

* cleanup 3

* PyTorch Hub models default to CUDA:0 if available

* device as string bug fix

* labels.png class names

* fontsize=10

* Integer printout

* test.py 'Labels'

* Update train.py

* GCP sudo docker

* cleanup

image weights compatible faster random index generator v2 for mosaic augmentation

* EMA bug fix 2

* update

* Enhanced model+EMA checkpointing

* update

* bug fix

* bug fix 2

* always save optimizer

* ema half

* remove model.float()

* model half

* carry ema/model in fp32

* rm model.float()

* both to float always

* cleanup

* cleanup