Add TensorRT Support and YOLOv5 (#100)

* [Add] Yolov5 trt HRNet inference on video (#99)

* [Add] Yolov5 trt HRNet inference on video

* Fixed a bug with int overflow on tracking

* Revisions before review

Co-authored-by: Giannis Pastaltzidis <gpastal@iti.gr>

* Restore submodule

* Rename models folder and remove pycache

* Add .gitignore

* Fix models imports

* Refactor code, Update docstring

* Fix YOLOv5 sizes and loading

* Rename models to fix issue with YOLOv5 from torch hub

* Fix issues with yolov5 and tensorrt, Update extract-keypoints script

* Fix bug in yolov5.engine detections

Fix bug in detection locations when tensorrt-converted yolov5 is used

* Add Google Colab notebook

* Update README.md

* Update notebook

Co-authored-by: gpastal24 <104021640+gpastal24@users.noreply.github.com>
Co-authored-by: Giannis Pastaltzidis <gpastal@iti.gr>

.gitignore

@@ -0,0 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/

.gitmodules

@@ -1,3 +1,3 @@
 [submodule "models/detectors/yolo"]
-	path = models/detectors/yolo
+	path = models_/detectors/yolo
 	url = https://github.com/eriklindernoren/PyTorch-YOLOv3

README.md

@@ -15,17 +15,20 @@ This repository provides:
 - A simple ``HRNet`` implementation in PyTorch (>=1.0) - compatible with official weights (``pose_hrnet_*``).
 - A simple class (``SimpleHRNet``) that loads the HRNet network for the human pose estimation, loads the pre-trained weights,
  and make human predictions on a single image or a batch of images.
-- **NEW** Support for "SimpleBaselines" model based on ResNet - compatible with official weights (``pose_resnet_*``).
-- **NEW** Support for multi-GPU inference.
-- **NEW** Add option for using YOLOv3-tiny (faster, but less accurate person detection).
-- **NEW** Add options for retrieving yolo bounding boxes and HRNet heatmaps.
-- Multi-person support with
+- Support for "SimpleBaselines" model based on ResNet - compatible with official weights (``pose_resnet_*``).
+- Support for multi-GPU inference.
+- Add options for retrieving yolo bounding boxes and HRNet heatmaps.
+- **NEW** Multi-person support with
  [YOLOv3](https://github.com/eriklindernoren/PyTorch-YOLOv3/tree/47b7c912877ca69db35b8af3a38d6522681b3bb3) 
- (enabled by default).  
+ (enabled by default), YOLOv3-tiny, or [YOLOv5](https://github.com/ultralytics/yolov5) by Ultralytics.
 - A reference code that runs a live demo reading frames from a webcam or a video file.
 - A relatively-simple code for training and testing the HRNet network.
 - A specific script for training the network on the COCO dataset. 
-- **NEW** A [Google Colab notebook](https://github.com/stefanopini/simple-HRNet/issues/84#issuecomment-908199736) showcasing how to use this repository - Sincere thanks to [@basicvisual](https://github.com/basicvisual) and [@wuyenlin](https://github.com/wuyenlin).
+- **NEW** An updated [Jupyter Notebook](https://github.com/stefanopini/simple-HRNet/blob/master/SimpleHRNet_notebook.ipynb) compatible with Google Colab showcasing how to use this repository.
+    - <a href="https://colab.research.google.com/github/stefanopini/simple-HRNet/blob/master/SimpleHRNet_notebook.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a> [Click here](https://colab.research.google.com/github/stefanopini/simple-HRNet/blob/master/SimpleHRNet_notebook.ipynb) to open the notebook on Colab!
+    - Thanks to [@basicvisual](https://github.com/basicvisual) and [@wuyenlin](https://github.com/wuyenlin) for the initial notebook.
+- **NEW** Support for TensorRT (thanks to [@gpastal24](https://github.com/gpastal24), see [#99](https://github.com/stefanopini/simple-HRNet/pull/99) and [#100](https://github.com/stefanopini/simple-HRNet/pull/100)).
+
 
 If you are interested in **HigherHRNet**, please look at [*simple-HigherHRNet*](https://github.com/stefanopini/simple-HigherHRNet) 
 
@@ -113,6 +116,24 @@ For help:
 python scripts/extract-keypoints.py --help
 ```
 
+### Converting the model to TensorRT:
+
+Warning: require the installation of TensorRT (see Nvidia website) and onnx.
+On some platforms, they can be installed with
+```
+pip install tensorrt onnx
+```
+
+Converting in FP16:
+```
+python scripts/export-tensorrt-model.py --device 0 --half
+```
+
+For help:
+```
+python scripts/export-tensorrt-model.py --help
+```
+
 ### Running the training script
 
 ```