Plumerai Documentation Overview¶
Plumerai People Detection¶
At Plumerai we've built the world’s most accurate people detection for the edge. We deliver a complete software solution for camera-based people detection. Our models are tiny and fast and detect people with a high accuracy in any situation. For more information about the product, see our people detection page.
These pages provide the technical documentation for our people detection products:
Additionally, we provide example usage of the People Detection library in the form of a simple OpenCV webcam-to-display pipeline. Documentation and source code is available in a GitHub repository.
Plumerai Inference Engine¶
We've also built the world’s fastest deep learning inference engine for Arm Cortex-M and other microcontrollers. You can find out more about the inference engine on our blog or try it out with your own model.
The technical documentation of the Plumerai Inference Engine can be found on different pages grouped per topic:
- Overview of the inference engine: Overview of the supported input model formats.
- Model format support: Overview of the supported input model formats.
- Layer and op support: Lists which neural network layers/ops are supported.
- Reporting and analysis: Information about the reporting and analysis options.
- Correctness validation: Details on how to run in validation mode to ensure correctness.
- Building and integration: Instructions on how to build and use the C++ API or C API.
- Example models: LeNet, MobileNetV2, an LSTM and a GRU-based RNN.