Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Updates to the TFLM Makfile that are not backwards compatible #46667

Closed
Lucy20211 opened this issue Jan 25, 2021 · 4 comments
Closed

Updates to the TFLM Makfile that are not backwards compatible #46667

Lucy20211 opened this issue Jan 25, 2021 · 4 comments
Assignees
Labels
comp:micro Related to TensorFlow Lite Microcontrollers TF 2.4 for issues related to TF 2.4 type:support Support issues

Comments

@Lucy20211
Copy link

Lucy20211 commented Jan 25, 2021

System information

  • OS Platform and Distribution: Linux Ubuntu 20.10
  • TensorFlow version: 2.4.1
  • Python version: 3.8
  • CPU Intel Core i7
  • GPU: NVIDIA GeForce GTX
  • STM32CubeIDE-Lnx: 1.3.0
  • STM32 Nucleo-64 development board

Describe the problem

I would like to run the Makefile in the Tensorflow Lite for Microcontrollers directory in order to run inference on ST microcontroller above. My problem is that I cannot use the
TAGS =”portable_optimized” command line option /cc @advaitjain

Source code / logs

tensorflow/lite/micro/tools/make/Makefile:61: *** The TAGS command line option is no longer supported in the TFLM Makefile..

Thanks in advance.

@advaitjain advaitjain added the comp:micro Related to TensorFlow Lite Microcontrollers label Jan 25, 2021
@advaitjain
Copy link
Member

The portable_optimized kernels have been removed for some time now. You can remove TAGS=portable_optimized from your command line and things should work as before.

@advaitjain
Copy link
Member

Also, since you're using an stm32f4 board, you might also want to try OPTIMIZED_KERNEL_DIR=cmsis_nn to get optimized implementations for some of the kernels.

@amahendrakar amahendrakar added TF 2.4 for issues related to TF 2.4 type:support Support issues labels Jan 27, 2021
@junior-azeh
Copy link

System information

  • OS Platform and Distribution: Linux Ubuntu 20.10
  • TensorFlow version: 2.4.1
  • Python version: 3.8
  • CPU Intel Core i7
  • GPU: NVIDIA GeForce GTX
  • STM32CubeIDE-Lnx: 1.3.0
  • STM32 Nucleo-64 development board

Describe the problem

I would like to run the Makefile in the Tensorflow Lite for Microcontrollers directory in order to run inference on ST microcontroller above. My problem is that I cannot use the TAGS =”portable_optimized” command line option /cc @advaitjain

Source code / logs

tensorflow/lite/micro/tools/make/Makefile:61: *** The TAGS command line option is no longer supported in the TFLM Makefile..

Thanks in advance.

Did you generate sample project to test with the stm32, if so what was the make command you used

System information

  • OS Platform and Distribution: Linux Ubuntu 20.10
  • TensorFlow version: 2.4.1
  • Python version: 3.8
  • CPU Intel Core i7
  • GPU: NVIDIA GeForce GTX
  • STM32CubeIDE-Lnx: 1.3.0
  • STM32 Nucleo-64 development board

Describe the problem

I would like to run the Makefile in the Tensorflow Lite for Microcontrollers directory in order to run inference on ST microcontroller above. My problem is that I cannot use the TAGS =”portable_optimized” command line option /cc @advaitjain

Source code / logs

tensorflow/lite/micro/tools/make/Makefile:61: *** The TAGS command line option is no longer supported in the TFLM Makefile..

Thanks in advance.

Did you generate sample projects for the stm32 board, what was the make command used

@Lucy20211
Copy link
Author

Hi, I used this command: make -f tensorflow/lite/micro/tools/make/Makefile (from https://www.digikey.com/en/maker/projects/tinyml-getting-started-with-tensorflow-lite-for-microcontrollers/c0cdd850f5004b098d263400aa294023)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
comp:micro Related to TensorFlow Lite Microcontrollers TF 2.4 for issues related to TF 2.4 type:support Support issues
Projects
None yet
Development

No branches or pull requests

4 participants