Hi,
I have a question about the OAK-1 Lite device's compatibility with Deeplabcut (DLC) for pose estimation. DLC supports exporting models in TensorFlow .pb format. Can the OAK-1 Lite work with such a model? I'm considering buying this device but am concerned about its performance. I'm looking for a few frames second nothing crazy. I plan to connect the camera to a Raspberry Pi for a personal project. The goal is to estimate my dog's poses and dispense treats when he performs a trick.
Deeplabcut: DeepLabCut/DeepLabCut
More information regarding the exported format:
Exporting DLC models
DeepLabCut enables the creating of tailored neuronal networks for pose estimation of user-defined bodyparts (4, 20). We sought to make these neural networks, which are TensorFlow graphs, easily deployable by developing a modelexport functionality. These customized DeepLabCut models can be created from standard trained DeepLabCut models by running the export_model function within DeepLabCut (see Methods), or models can be downloaded from the new DeepLabCut Model Zoo.
The model export module utilizes the protocol buffer format (.pb file). Protocol buffers are a language-neutral, platformneutral extensible mechanism for serializing structured data^2^, which makes sharing models simple. Sharing a whole (DeepLabCut) project is not necessary, and an end-user can simply point to the protocol buffer file of a model to run inference on novel videos (online or offline). The flexibility offered by the protocol buffer format allowed us to integrate DeepLabCut into applications written in different languages: a new python package DeepLabCut-Live!, which facilitates loading DeepLabCut networks to run inference; and into Bonsai, which is written in C# and runs DeepLabCut inference using TensorFlowSharp^3^.