* Fix early create subscribers for rgbd hand gesture recognition node

* Fix missing option for output topic name in ros node intialization

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* refactor: Updated download paths of EfficientPS pretrained models

* refactor: Updated download path of EfficientPS test data

Co-authored-by: Niclas <49001036+vniclas@users.noreply.github.com>

* Resize image data instead of assuming size of 224x224

* Update docstring

* Update device code selection

* Update argument names and default values for consistency across nodes

* Add blank line

* Update projects/opendr_ws/src/perception/scripts/audiovisual_emotion_recognition.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Move subscribers to after init_node

Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>
Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update device code selection

* Update arguments name and default value

* Update parameter selection in argparse

* Update docstring in callback

* Update output topic name and add option for output topic name

* Update projects/opendr_ws/src/perception/scripts/heart_anomaly_detection.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update projects/opendr_ws/src/perception/scripts/heart_anomaly_detection.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update projects/opendr_ws/src/perception/scripts/heart_anomaly_detection.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

* Update device code selection

* Update arguments name in ros node class

* Fix docstring in callback method

* Update from single quotes to double quotes

* Update argparse

* Add output topic name selection in argparse

* Update projects/opendr_ws/src/perception/scripts/speech_command_recognition.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

* Add argument parser for device parameter and update device selection

* Change rosnode argument name to be consistent with other nodes

* Add argument parser and update default value of rgb and depth image inputs, update docstring

* rgbd_hand_gesture_recognition.py

* Update projects/opendr_ws/src/perception/scripts/rgbd_hand_gesture_recognition.py

Modify queue size to avoid delays

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Change gesture topic parameter name

* Add blank lines and use double-quotes for docstring

* Fix wrong arguments name in docstring in preprocess method

* Change argument name in callback method

* Add an argument for output topic name

* Update output topic

* Fix docstring in preprocess method

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

merge `master` into `develop`

* Update ROS1 video_activity_recognition script

* Remove repeat rrospy.Subscriber

* Update projects/opendr_ws/src/perception/scripts/video_activity_recognition.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update projects/opendr_ws/src/perception/scripts/video_activity_recognition.py

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update _resize in video_activity_recognition.py

* Fix linting issue

* Fix video har ros node double-max and float warn

* Remove unused import

Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>

* Update docker test to the latest version

* Update docker version in installation.md

Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>
Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Adding Nanodet implementation

* add some changes

* Finall changes, demos are done, configs alterd and better dataset implementation for ExternalDatasets. Test nanodet impelentation added

* for tx2 and nx testing

* Fix bug with save and loads, docs, added verbose in all methods, discart some unused code

* new changes for inference and load - save for opendr standarts.

* delete unused code and pep8 fixes

* temp

* pep8 fixes and deleted unused code

* tutorial

* .gitmodules fix

* name changes for easier use

* pep8 fixes

* pep8 fixes, unused code deletion, bug fixes

* ignore licensed from third party, bug fixes in tests

* bug fixes in test and memory alocation

* new implementation for changes in learner

* Revert change

* undo change

* Undo change

* Add nanodet test

* Add nanodet tests

* delete unwanted script

* specify device in all cases

* bug fix

* pep8 fix

* Added missing __init__.py

* Added missing __init__.py

* pep8 fix

* pep8 fix

* Added missing __init__.py

* Added missing __init__.py

* ros node implementation of Nanodet toolkit

* Update projects/opendr_ws/src/perception/README.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update projects/opendr_ws/src/perception/README.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update projects/perception/object_detection_2d/nanodet/README.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update src/opendr/perception/object_detection_2d/nanodet/algorithm/config/config_file_detail.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update src/opendr/perception/object_detection_2d/nanodet/algorithm/config/config_file_detail.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update src/opendr/perception/object_detection_2d/nanodet/algorithm/config/config_file_detail.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update src/opendr/perception/object_detection_2d/nanodet/algorithm/config/config_file_detail.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update src/opendr/perception/object_detection_2d/nanodet/algorithm/config/config_file_detail.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* changes from the comment for better readability and some fixes in ReadMe and dock files.

* exclude termcolor and fix typo

* changes to merge with the new develop branch

Co-authored-by: passalis <passalis@csd.auth.gr>
Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com>
Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>
Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

merge `master` into `develop`

* Pose est: Added lambda expression in argparse to handle passing of none value and minor optimization

* Face reco: Added lambda expression in argparse to handle passing of none value

* Fall det: Added lambda expression in argparse to handle passing of none value and some fixes in callback

* Fixed whole fall detection list being published for each fallen pose

* Fallen message now publishes only when there is a fall detected

* Each fallen pose now has different id

* Face det: Added lambda expression in argparse to handle passing of none value and minor optimization

* Obj det 2d: Added lambda expression in argparse to handle passing of none value and minor optimization

* Sem segm: Added lambda expression in argparse to handle passing of none value

* Moved pose bounding box calculation inside if block

* removed wrongly placed file

* Update README.md

* restructured projects

* Update README.md

* Create README.md

* removed __init__.py

* Create issues.md

* Update issues.md

* Update customize.md

* Update README.md

* Apply suggestions from code review

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Link updated

* Update index.md

* Updated released index

* Update index.md

* Fix old link

* Update test_license.py

* Updated projects path

* Updated links to projects

* Updated links to projects

* Fixed projects path

* pep8 fixes

* Categorized nodes according to their input

* Custom model loading example

* Issues for colab

* Update issues.md

* Update projects/opendr_ws/README.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Fixed type conversion bug

* Added conditionals in download method to not re-download existing files

* Simplified else-ifs as suggested by review

Merge `master` branch into `develop` branch

* include 3d detection test

* fix np bool warning

* Revert "fix np bool warning"

This reverts commit ec21061620ac0229c37cbf2d9c47e82ae5d9d639.

* Remove del learner

* Eneable tracking 3d tests

* Add init for 2d tracking tests

* Update 3D tracking dependencies

* Docker, installation and documentation improvements  (#276)

* docker fixes

* Style fixes

* Create customize.md

* Removed docker building instructions

* Update customize.md

* Update customize.md

* Update installation.md

* Update customize.md

* Added link for customization

* Update docs/reference/installation.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update docs/reference/installation.md

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Update docs/reference/installation.md

Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>
Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>

* DetectionDataset evaluation fix for empty detections (#285)

* Checkout specific detectron commit

* Install specific detectron2 commit

* Point to specific detectron2 commit

* Update installation.md

* Update dependencies.ini

* Update dependencies.ini

* Update requirements.txt

* Update dependencies.ini

* Update dependencies.ini

* Update requirements.txt

* Update to support newer skimage version

* Clarified purpose and limitations of fall detection tool (#280)

* Enable All 3d test

* Fix slow data preparation for KITTI

* Simplify 3d detection tests

* Fix unclosed file

* Fix repeated eval failure

* Cleanup

* Cleanup

* Cleanup

* Remove unused test functions

Co-authored-by: Nikolaos Passalis <passalis@users.noreply.github.com>
Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>
Co-authored-by: ad-daniel <44834743+ad-daniel@users.noreply.github.com>
Co-authored-by: vivinousi <32997432+vivinousi@users.noreply.github.com>
Co-authored-by: Kostas Tsampazis <27914645+tsampazk@users.noreply.github.com>
Co-authored-by: ad-daniel <daniel.dias@epfl.ch>

* Download pre-trained model weights

* Add backward compatibility

* Do not remove downloaded checkpoint file

* Resolve PEP8 issue

* Consistent with ROS2

* Address review

* Reduce queue size to 1

* Set default for input rgb image topic

* Updated, cleaned up and added argparse to ROS1 pose estimation node

* Added additional information for pose estimation node documentation

* Improved wording in pose estimation ros docs

* Minor comment improvement

* Fix typo

* Updated, cleaned up and added argparse to ROS1 fall detection node

* Added box id type conversion that caused error in object det2d centernet

* Updated, cleaned up and added argparse to ROS1 object detection 2d centernet node

* Updated, cleaned up and added argparse to ROS1 object detection 2d ssd node

* Updated, cleaned up and added argparse to ROS1 object detection 2d yolov3 node

* Minor typo fix

* Updated, cleaned up and added argparse to ROS1 object detection 2d DETR node

* Updated, cleaned up and added argparse to ROS1 face detection retinaface node

* Updated, cleaned up and added argparse to ROS1 semantic segmentation bisenet node

* Increased buffer size for fall detection and pose estimation to minimize delay

* Updated, cleaned up and added argparse to ROS1 face recognition node

* Fixed minor type conversion typo in bridge

* Sem seg bisenet now outputs class ids heatmap and separate visualization heatmap with improved colors and legend

* Added custom opendr pose and keypoint messages on ros_bridge

* Modified opendr_bridge from/to ros pose to use new messages and doc update

* ROS1 pose node now uses new custom pose ros message

* Enhanced pose __str__ method to return pose id and confidence

* Update human_model_generation_client.py

* Added missing space to pose out_string

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

* Fixed indentation on CMakeLists.txt

Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>

Co-authored-by: charsyme <63857415+charsyme@users.noreply.github.com>
Co-authored-by: Stefania Pedrazzi <stefaniapedrazzi@users.noreply.github.com>