experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Fixing the markdown and disabling internal auto-formatting.

Browse Source
This commit is contained in:
Advait Jain 2020-10-19 14:21:00 -07:00
parent db14325178
commit c702a443f5
2 changed files with 57 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

64
tensorflow/lite/micro/cortex_m_generic/README.md
View File

@ -1,3 +1,5 @@
<!-- mdformat off(b/169948621#comment2) -->
# Generic Cortex-Mx customizations # Generic Cortex-Mx customizations
The customization requires a definition where the debug log goes to. The purpose The customization requires a definition where the debug log goes to. The purpose
@ -13,42 +15,50 @@ See debug_log_callback.h
# How to build # How to build
Required parameters: - TARGET: cortex_m_generic - TARGET_ARCH: cortex-mXX (For Required parameters:
all options see:
tensorflow/lite/micro/tools/make/targets/cortex_m_generic_makefile.inc)
Optional parameters: - TOOLCHAIN: armgcc (default) or armmclang - For - TARGET: cortex_m_generic
Cortex-M55, ARM Compiler 6.14 or later is required. - TARGET_ARCH: cortex-mXX (For all options see: tensorflow/lite/micro/tools/make/targets/cortex_m_generic_makefile.inc)
Optional parameters:
- TOOLCHAIN: armgcc (default) or armmclang
- For Cortex-M55, ARM Compiler 6.14 or later is required.
Some examples: Some examples:
Building with arm-gcc ``` make -f tensorflow/lite/micro/tools/make/Makefile Building with arm-gcc
TARGET=cortex_m_generic TARGET_ARCH=cortex-m7 microlite make -f ```
tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m7 microlite
TARGET_ARCH=cortex-m7 TAGS=cmsis-nn microlite make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m7 TAGS=cmsis-nn microlite
make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m4 TAGS=cmsis-nn microlite
TARGET_ARCH=cortex-m4 TAGS=cmsis-nn microlite make -f make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m4+fp TAGS=cmsis-nn microlite
tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic ```
TARGET_ARCH=cortex-m4+fp TAGS=cmsis-nn microlite ```
Building with armclang `make -f tensorflow/lite/micro/tools/make/Makefile Building with armclang
TOOLCHAIN=armclang TARGET=cortex_m_generic TARGET_ARCH=cortex-m55 microlite make
-f tensorflow/lite/micro/tools/make/Makefile TOOLCHAIN=armclang ```
TARGET=cortex_m_generic TARGET_ARCH=cortex-m55 TAGS=cmsis-nn microlite make -f make -f tensorflow/lite/micro/tools/make/Makefile TOOLCHAIN=armclang TARGET=cortex_m_generic TARGET_ARCH=cortex-m55 microlite
tensorflow/lite/micro/tools/make/Makefile TOOLCHAIN=armclang make -f tensorflow/lite/micro/tools/make/Makefile TOOLCHAIN=armclang TARGET=cortex_m_generic TARGET_ARCH=cortex-m55 TAGS=cmsis-nn microlite
TARGET=cortex_m_generic TARGET_ARCH=cortex-m55+nofp TAGS=cmsis-nn microlite` make -f tensorflow/lite/micro/tools/make/Makefile TOOLCHAIN=armclang TARGET=cortex_m_generic TARGET_ARCH=cortex-m55+nofp TAGS=cmsis-nn microlite
```
The Tensorflow Lite Micro makefiles download a specific version of the arm-gcc The Tensorflow Lite Micro makefiles download a specific version of the arm-gcc
compiler to tensorflow/lite/micro/tools/make/downloads/gcc_embedded. If desired, compiler to tensorflow/lite/micro/tools/make/downloads/gcc_embedded.
a different version can be used by providing `TARGET_TOOLCHAIN_ROOT` option to
the Makefile. `make -f tensorflow/lite/micro/tools/make/Makefile If desired, a different version can be used by providing `TARGET_TOOLCHAIN_ROOT`
TARGET=cortex_m_generic TARGET_ARCH=cortex-m4 option to the Makefile:
TARGET_TOOLCHAIN_ROOT=/path/to/arm-gcc/ microlite`
```
make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m4+fp TARGET_TOOLCHAIN_ROOT=/path/to/arm-gcc/ microlite
```
Similarly, `TAGS=cmsis-nn` downloads a specific version of CMSIS to Similarly, `TAGS=cmsis-nn` downloads a specific version of CMSIS to
tensorflow/lite/micro/tools/make/downloads/cmsis. While this is the only version tensorflow/lite/micro/tools/make/downloads/cmsis. While this is the only version
that is regularly tested, you can use your own version of CMSIS as well by that is regularly tested, you can use your own version of CMSIS as well by
providing `CMSIS_PATH` to the Makefile: `make -f providing `CMSIS_PATH` to the Makefile:
tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic
TARGET_ARCH=cortex-m4 TAGS=cmsis-nn CMSIS_PATH=/path/to/own/cmsis microlite` ```
make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARGET_ARCH=cortex-m4+fp TAGS=cmsis-nn CMSIS_PATH=/path/to/own/cmsis microlite
```

39
tensorflow/lite/micro/docs/memory_management.md
View File

@ -1,3 +1,5 @@
<!-- mdformat off(b/169948621#comment2) -->
<!-- <!--
Semi-automated TOC generation with instructions from Semi-automated TOC generation with instructions from
https://github.com/ekalinin/github-markdown-toc#auto-insert-and-update-toc https://github.com/ekalinin/github-markdown-toc#auto-insert-and-update-toc
@ -38,13 +40,14 @@ sections:
The illustration below represents typical allocations in TFLM: The illustration below represents typical allocations in TFLM:
## ``` ```
--------------------------------------------------------------------------------
| | | | | HEAD |<-- TEMPORARY -->| TAIL | | | | |
| HEAD |<-- TEMPORARY -->| TAIL |
## | | | | | | | |
--------------------------------------------------------------------------------
* Lowest Address Highest Address * ``` * Lowest Address Highest Address *
```
### Head Section ### Head Section
@ -129,20 +132,18 @@ interpreter.PrintAllocations();
The output of this call will look something similar to this (output from the The output of this call will look something similar to this (output from the
[memory_arena_threshold_test](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/memory_arena_threshold_test.cc#L205)): [memory_arena_threshold_test](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/memory_arena_threshold_test.cc#L205)):
`sh [RecordingMicroAllocator] Arena allocation total 9568 bytes
```bash
[RecordingMicroAllocator] Arena allocation total 9568 bytes
[RecordingMicroAllocator] Arena allocation head 7744 bytes [RecordingMicroAllocator] Arena allocation head 7744 bytes
[RecordingMicroAllocator] Arena allocation tail 1824 bytes [RecordingMicroAllocator] Arena allocation tail 1824 bytes
[RecordingMicroAllocator] 'TfLiteEvalTensor data' used 360 bytes with alignment [RecordingMicroAllocator] 'TfLiteEvalTensor data' used 360 bytes with alignment overhead (requested 360 bytes for 15 allocations)
overhead (requested 360 bytes for 15 allocations) [RecordingMicroAllocator] [RecordingMicroAllocator] 'Persistent TfLiteTensor data' used 0 bytes with alignment overhead (requested 0 bytes for 0 tensors)
'Persistent TfLiteTensor data' used 0 bytes with alignment overhead (requested 0 [RecordingMicroAllocator] 'Persistent TfLiteTensor quantization data' used 0 bytes with alignment overhead (requested 0 bytes for 0 allocations)
bytes for 0 tensors) [RecordingMicroAllocator] 'Persistent TfLiteTensor [RecordingMicroAllocator] 'TfLiteTensor variable buffer data' used 0 bytes with alignment overhead (requested 0 bytes for 0 allocations)
quantization data' used 0 bytes with alignment overhead (requested 0 bytes for 0 [RecordingMicroAllocator] 'NodeAndRegistration struct' used 392 bytes with alignment overhead (requested 392 bytes for 7 NodeAndRegistration structs)
allocations) [RecordingMicroAllocator] 'TfLiteTensor variable buffer data' used [RecordingMicroAllocator] 'Operator runtime data' used 136 bytes with alignment overhead (requested 136 bytes for 5 OpData structs)
0 bytes with alignment overhead (requested 0 bytes for 0 allocations) ```
[RecordingMicroAllocator] 'NodeAndRegistration struct' used 392 bytes with
alignment overhead (requested 392 bytes for 7 NodeAndRegistration structs)
[RecordingMicroAllocator] 'Operator runtime data' used 136 bytes with alignment
overhead (requested 136 bytes for 5 OpData structs)`
### Allocation Section Details ### Allocation Section Details