mirror of https://github.com/vee1e/tflite-micro - Infrastructure to enable deployment of ML models to low-powe
Find a file
suleshahid 15092dfdba
IF kernel nulltpr fix (#2515)
In some cases if you IF op has 0 outputs, it can reference a nullptr in trying to access node->outputs->size(). This is in the case if your model was flatbuffer_aligned which most likely optimizes away the empty array to nullptr.

BUG=[328527454](https://buganizer.corp.google.com/issues/328527454)
2024-03-21 21:54:02 +00:00
.github Remove Wave as dependency (#2508) 2024-03-15 14:04:11 -07:00
ci Remove Wave as dependency (#2508) 2024-03-15 14:04:11 -07:00
codegen codegen: Remove make helpers for codegen (#2378) 2024-01-09 19:54:12 +00:00
data/continuous_builds
docs Change comment to refer to 3.11 instead of 3.9 (#2029) 2023-06-08 18:11:59 +00:00
python Automated sync from github.com/tensorflow/tensorflow (#2510) 2024-03-18 22:09:28 +00:00
signal Unique Init, Prepare, Eval functions of signal kernels. (#2497) 2024-03-11 22:19:08 +00:00
tensorflow IF kernel nulltpr fix (#2515) 2024-03-21 21:54:02 +00:00
third_party Remove the output_to_genfiles = True parameter from Starlark rules (#2512) 2024-03-19 21:56:48 +00:00
tools Add expand_stamp_vars docstring and fix import (#2178) 2023-08-21 16:53:10 +00:00
.bazelrc Fix bazel 7.0 bzlmod update (#2352) 2023-12-12 00:35:03 +00:00
.bazelversion build(bazel): pin bazel version to 7.0.0 (#2360) 2024-01-03 20:53:21 +00:00
.clang-format
.editorconfig style: add a project-level .editorconfig file (#1968) 2023-05-12 21:18:08 +00:00
.gitignore build: add target to generate compiler_commands.json (#1658) 2023-01-13 05:13:47 +00:00
AUTHORS
BUILD build: add target to generate compiler_commands.json (#1658) 2023-01-13 05:13:47 +00:00
CODEOWNERS Add rascani@ as CODEOWNER for ci and .github directories. (#2042) 2023-06-12 20:19:54 +00:00
CONTRIBUTING.md Remove Wave as dependency (#2508) 2024-03-15 14:04:11 -07:00
debugging_output.md Adding ReadMe for Layer by Layer Debug Targets (#2305) 2023-11-28 22:06:25 +00:00
LICENSE
README.md refactor(python): move runtime to package-friendly directory structure (#2051) 2023-06-15 06:25:19 +00:00
SECURITY.md
WORKSPACE Replace tensorflow-cpu usage with tensorflow (#2396) 2024-02-23 00:35:22 +00:00

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

Official Builds

Build Type Status
CI (Linux) CI
Code Sync Sync from Upstream TF

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
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

Community Supported Kernels and Unit Tests

This is a list of targets that have optimized kernel implementations and/or run the TFLM unit tests using software emulation or instruction set simulators.

Build Type Status
Cortex-M Cortex-M
Hexagon Hexagon
RISC-V RISC-V
Xtensa Xtensa
Generate Integration Test Generate Integration Test

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