What is Detection Metrics?
Detection Metrics is an application that provides a toolbox of utilities oriented to simplify the development and testing of solutions based on object detection. The application comes with a GUI (based on Qt) but it can also be used through command line.
What’s supported in Detection Metrics.
|Supported OS||Multiplatform using Docker|
|Supported inputs in Deployer||
The application is designed to experiment with datasets and neural networks using various frameworks. Currently it comes with the following utilities:
- Viewer: view the dataset images with the annotations.
- Detector: run a model over a dataset and get generate a new annotated dataset.
- Evaluator: evaluate the ground truth dataset with another one and get the comparison metrics.
- Deployer: run a model over different inputs like a video or webcam and generate a new annotated dataset.
- Converter: convert a dataset into another dataset format.
- Command line application (CLI): access Detection Metrics toolset through command line
- Detection Metrics as ROS Node: use Detection Metrics as a ROS Node.
- Labelling: add or modify labels in the datasets in runtime when running Deployer
Every tool in Detection Metrics requires a config file to run, where the main parameters needed are provided. Currently, YAML config file format is supported. See below on how to create a custom config file.
Each tool may have different requirements for keys in config file, and they can be known by passing the
--help flag when using Detection Metrics from
the command line.
Creating a custom
It is recommended to create and assign a dedicated directory for storing all datasets, weights and config files, for easier access and a cleaner
For instance, we will be using
/opt/datasets/ for demonstration purposes.
Create the following directories in
Again, these names are just examples and can be changed, but must also be changed in
cfg: This directory will store config files for various networks. For example, yolo-voc.cfg.
names: This directory will contain class names for various datasets. For example, voc.names.
weights: This directory will contain weights for various networks, such as yolo-voc.weights for YOLO or a frozen inference graph for Tensorflow trained networks.
eval: Evaluations path.
Once completed, you can create your own custom appConfig.yml like the one mentioned. For example:
datasetPath: /opt/datasets/ evaluationsPath: /opt/datasets/eval weightsPath: /opt/datasets/weights netCfgPath: /opt/datasets/cfg namesPath: /opt/datasets/names inferencesPath: /opt/datasets
Place your weights in weights directory, config files in cfg directory, classname files in names. And you are ready to go ⚡️ .
General Detection Metrics GUI
The top toolbar shows the different tools available.
Example of detection and console output in Detection Metrics
Two image views are displayed, one with the ground truth and the other with the detected annotations. In the console output, log info is shown.