Technical content and expertise to help jump start your design and get you to production faster.
Start your designDownload our latest development and embedded software solutions.
Expedite time-to-market with our extensive lineup of development kits.
Jump-start your design with proven hardware and software solutions.
Get the latest specifications in our technical documentation library.
Further your technical expertise with online and in-person instruction.
Get comprehensive paid support to fast-track your product development.
Design ideas, demo videos, quality answers. Connect with NXP professionals and other knowledgeable designers ready to help.
Software, documentation, evaluation tools. The resources to build comprehensive solutions and accelerate your time to market.
Access our design resource libraryWe're always looking for passionate and talented people to work with us.
Join our teamIntegrated in MCUXpresso and Yocto development environments, eIQ delivers TensorFlow Lite for NXP’s MCU and MPU platforms. Developed by Google to provide reduced implementations of TensorFlow (TF) models, TF Lite uses many techniques for achieving low latency such as pre-fused activations and quantized kernels that allow smaller and (potentially) faster models. Furthermore, like TensorFlow, TF Lite utilizes the Eigen library to accelerate matrix and vector arithmetic.
TF Lite defines a model file format, based on FlatBuffers. Unlike TF’s protocol buffers, FlatBuffers have a memory footprint an order of magnitude smaller allowing better use of cache lines, leading to faster execution on NXP devices. Although TF Lite supports a subset of TF neural network operations, it still maintains a wide range of supported operations (~50), thereby allowing the use of more advanced models compared to CMSIS-NN. It also supports recurrent neural networks (RNNs) and the even more complex long short-term memory (LSTM) cells.