uTensor is an extremely light-weight machine learning inference framework built on Mbed and Tensorflow. It consists of a runtime library and an offline tool. The total size of graph definition and algorithm implementation of a 3-layer MLP produced by uTensor is less than 32kB in the resulting binary (excluding the weights).
Features #
- Convolution
- Pooling
- CMSIS-NN integration
- Smaller binary
- More efficient Run-time
Resources #
- utensor_cgen. C++ code generator for uTensor https://utensor-cgen.readthedocs.io/en/latest/.
- oscw18-edge-ai. Analysys of edge computing resources for cubesats.
- utensor-mnist-demo. Handwritten digit recognition demo.