experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
rei/fork-r2.3
STT-tensorflow/tensorflow/lite/micro/benchmarks
History
Nick Kreeger b6d13bb0a8 Remove TF Micro tests that use the "name" field in TfLiteTensor. 
The TFLM team is preparing to provide an "optimized" memory build option. This build option will eliminate non-needed/essential fields from core TFLite structs. The first big change is to reduce the number of pointers on TfLiteTensor. Many models have multiple tensors (e.g. benchmark keyword has 54) and each pointer adds up for TFLM. This cleanup pass removes the soon to be un-used 'name' field from TfLiteTensor.

PiperOrigin-RevId: 316000388
Change-Id: I230865014d5a59b78c1c1c9f5eda784f6d611e77
2020-06-11 16:42:03 -07:00
..
BUILD Add a memory threshold allocation test for the Keyword model. 2020-06-11 12:54:09 -07:00
conv_benchmark.cc Remove TF Micro tests that use the "name" field in TfLiteTensor. 2020-06-11 16:42:03 -07:00
depthwise_conv_benchmark.cc Remove TF Micro tests that use the "name" field in TfLiteTensor. 2020-06-11 16:42:03 -07:00
keyword_benchmark.cc Restrict visibility for micro libraries. 2020-06-10 11:35:26 -07:00
keyword_scrambled_model_data.cc Align example models to 64-bit boundaries to guarantee correctness for all 64-bit flatbuffer accesses. Aligning 64-bit datatypes to 32-bits can cause memory errors on some architectures. 2020-05-20 15:48:12 -07:00
keyword_scrambled_model_data.h Create keyword spotting benchmark. Keyword model has scrambled weights, so it will only function as a benchmark for performance optimizations. 2020-04-14 14:00:37 -07:00
Makefile.inc Create a benchmark for the person detection model. 2020-04-21 12:46:03 -07:00
micro_benchmark.h Restrict visibility for micro libraries. 2020-06-10 11:35:26 -07:00
person_detection_benchmark.cc Restrict visibility for micro libraries. 2020-06-10 11:35:26 -07:00
README.md Create a benchmark for the person detection model. 2020-04-21 12:46:03 -07:00

README.md

TFLite for Microcontrollers Benchmarks

These benchmarks are for measuring the performance of key models and workloads. They are meant to be used as part of the model optimization process for a given platform.

Table of contents

Keyword benchmark

The keyword benchmark contains a model for keyword detection with scrambled weights and biases. This model is meant to test performance on a platform only. Since the weights are scrambled, the output is meaningless. In order to validate the accuracy of optimized kernels, please run the kernel tests.

Person detection benchmark

The keyword benchmark provides a way to evaluate the performance of the 250KB visual wakewords model.

Run on x86

To run the keyword benchmark on x86, run

make -f tensorflow/lite/micro/tools/make/Makefile TAGS=posix test_keyword_benchmark

To run the person detection benchmark on x86, run

make -f tensorflow/lite/micro/tools/make/Makefile TAGS=posix test_person_detection_benchmark

Run on Xtensa XPG Simulator

To run the keyword benchmark on the Xtensa XPG simulator, you will need a valid Xtensa toolchain and license. With these set up, run:

make -f tensorflow/lite/micro/tools/make/Makefile TARGET=xtensa-xpg XTENSA_CORE=<xtensa core>  TAGS=xtensa_hifimini test_keyword_benchmark -j18

Run on Sparkfun Edge

The following instructions will help you build and deploy this benchmark on the SparkFun Edge development board.

If you're new to using this board, we recommend walking through the AI on a microcontroller with TensorFlow Lite and SparkFun Edge codelab to get an understanding of the workflow.

Build binary using

make -f tensorflow/lite/micro/tools/make/Makefile TARGET=sparkfun_edge person_detection_benchmark_bin

Refer to flashing instructions in the Person Detection Example.