vee1e/tflite-micro
1
0
Fork 0
mirror of https://github.com/vee1e/tflite-micro.git synced 2026-09-01 17:57:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
mirror of https://github.com/vee1e/tflite-micro - Infrastructure to enable deployment of ML models to low-powe
1965 commits 13 branches 0 tags 36 MiB
Find a file
Ryan Kuester f26158b1be
feat(compression): use DECODE operators in output models (#3654) 
Rewrite the compression tool to produce models that decompress
tensors at runtime through DECODE operators. Drop the legacy output
format, a metadata flatbuffer embedded in the model.

Route each tensor's compression through a dispatch table that selects
a plugin by the spec's compression method type. Look-up-table
compression is the only method implemented; the Huffman and pruning
plugins are stubs that exist to validate the plugin interface.

Update unit tests accordingly.

BUG=part of #3256
2026-08-12 15:42:41 +00:00
.github Added allow-unsafe-pr-checkout: true (#3615) 2026-07-01 13:59:22 -07:00
ci Manual sync from sync from github.com/tensorflow/tensorflow (#3601) 2026-07-01 14:46:41 -07:00
data/continuous_builds
docs [Doc] Fix typos (#3446) 2026-02-11 17:18:49 +00:00
python fix(pypi): repair wheel build for bzlmod (#3653) 2026-08-11 14:53:45 +00:00
signal Bazel Module (#3364) 2026-02-11 14:11:47 -08:00
tensorflow feat(compression): use DECODE operators in output models (#3654) 2026-08-12 15:42:41 +00:00
third_party [CI] Clean up bzl (#3478) 2026-02-12 14:05:54 -08:00
tools Clean-up unused bzl load (#3576) 2026-05-26 22:55:55 +00:00
.bazelignore
.bazelrc +build:windows_ci --build_python_zip=false (#3462) 2026-02-12 09:33:55 -08:00
.bazelversion Bazel 8.7.0 (#3610) 2026-06-30 15:23:57 -07:00
.clang-format
.editorconfig
.gitignore
.style.yapf
AUTHORS
BUILD build(bazel): inject tflite_micro shim via tflm_py_* wrappers (#3573) 2026-05-26 19:51:58 +00:00
CODEOWNERS
CONTRIBUTING.md [Doc] Fix typos (#3446) 2026-02-11 17:18:49 +00:00
debugging_output.md
LICENSE
MODULE.bazel Bazel 8.7.0 (#3610) 2026-06-30 15:23:57 -07:00
MODULE.bazel.lock Bazel 8.7.0 (#3610) 2026-06-30 15:23:57 -07:00
README.md Added Error Handling & Defensive Programming Guide (#3539) 2026-06-30 22:24:50 +00:00
SECURITY.md
tflite_micro.py Bazel Module (#3364) 2026-02-11 14:11:47 -08:00

README.md

TensorFlow Lite for Microcontrollers

TensorFlow Lite for Microcontrollers is a port of TensorFlow Lite designed to run machine learning models on DSPs, microcontrollers and other devices with limited memory.

Additional Links:

Build Status

CI Status

Group Status
Core CI CI Sync
Targets Cortex-M RISC-V Hexagon Xtensa
Misc Generate Integration Test

Community Supported TFLM Examples

This table captures platforms that TFLM has been ported to. Please see New Platform Support for additional documentation.

Platform Status
Arduino Arduino Antmicro
Coral Dev Board Micro TFLM + EdgeTPU Examples for Coral Dev Board Micro
Espressif Systems Dev Boards ESP Dev Boards
Ingenic MIPS Boards Ingenic MIPS Boards
Renesas Boards TFLM Examples for Renesas Boards
Silicon Labs Dev Kits TFLM Examples for Silicon Labs Dev Kits
Sparkfun Edge Sparkfun Edge
Texas Instruments Dev Boards Texas Instruments Dev Boards

Contributing

See our contribution documentation.

Getting Help

A Github issue should be the primary method of getting in touch with the TensorFlow Lite Micro (TFLM) team.

The following resources may also be useful:

  1. SIG Micro email group and monthly meetings.

  2. SIG Micro gitter chat room.

  3. For questions that are not specific to TFLM, please consult the broader TensorFlow project, e.g.:

Additional Documentation

RFCs

  1. Pre-allocated tensors
  2. TensorFlow Lite for Microcontrollers Port of 16x8 Quantized Operators