make -f tensorflow/lite/micro/tools/make/Makefile TARGET=sparkfun_edge person_detection_benchmark_bin
```
Refer to flashing instructions in the [Person Detection Example](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/person_detection/README.md#running-on-sparkfun-edge).
Refer to flashing instructions in the [Person Detection Example](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/person_detection/README.md#running-on-sparkfun-edge).
This more complex case shows that you can also add helper source files alongside
the main implementation, as long as you
[mention them in the platform-specific makefile](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/CMSIS/Makefile.inc).
[mention them in the platform-specific makefile](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/CMSIS/Makefile.inc).
You can also do things like update the list of libraries that need to be linked
@@ -500,7 +500,7 @@ for filename in glob.glob("mbed-os/tools/profiles/*.json"):
```
Note: Mbed has a dependency to an old version of arm_math.h and cmsis_gcc.h (adapted from the general [CMSIS-NN MBED example](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/kernels/cmsis_nn#example-2---mbed)). Therefore you need to copy the newer version as follows:
Note: Mbed has a dependency to an old version of arm_math.h and cmsis_gcc.h (adapted from the general [CMSIS-NN MBED example](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/kernels/cmsis_nn#example-2---mbed)). Therefore you need to copy the newer version as follows:
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Redirect","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyO1u6oks1qPVEQNnHFD3Cyo"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"markdown","metadata":{"id":"86C-FMxpdZxv","colab_type":"text"},"source":["This Colab notebook has been moved to [https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb)\n"]}]}
\ No newline at end of file
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Redirect","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyO1u6oks1qPVEQNnHFD3Cyo"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"markdown","metadata":{"id":"86C-FMxpdZxv","colab_type":"text"},"source":["This Colab notebook has been moved to [https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb)\n"]}]}
"Deep learning networks learn to model patterns in underlying data. Here, we're going to train a network to model data generated by a [sine](https://en.wikipedia.org/wiki/Sine) function. This will result in a model that can take a value, `x`, and predict its sine, `y`.\n",
"\n",
"The model created in this notebook is used in the [hello_world](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/hello_world) example for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview).\n",
"The model created in this notebook is used in the [hello_world](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world) example for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview).\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" </td>\n",
"</table>"
]
...
...
@@ -3446,11 +3446,11 @@
"source": [
"## Deploy to a Microcontroller\n",
"\n",
"Follow the instructions in the [hello_world](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/hello_world) README.md for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview) to deploy this model on a specific microcontroller.\n",
"Follow the instructions in the [hello_world](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world) README.md for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview) to deploy this model on a specific microcontroller.\n",
"\n",
"**Reference Model:** If you have not modified this notebook, you can follow the instructions as is, to deploy the model. Refer to the [`hello_world/train/models`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/models) directory to access the models generated in this notebook.\n",
"**Reference Model:** If you have not modified this notebook, you can follow the instructions as is, to deploy the model. Refer to the [`hello_world/train/models`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/train/models) directory to access the models generated in this notebook.\n",
"\n",
"**New Model:** If you have generated a new model, then update the values assigned to the variables defined in [`hello_world/model.cc`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/model.cc) with values displayed after running the following cell."
"**New Model:** If you have generated a new model, then update the values assigned to the variables defined in [`hello_world/model.cc`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/hello_world/model.cc) with values displayed after running the following cell."
It's a fairly small amount of code that creates an interpreter, gets a handle to
a model that's been compiled into the program, and then invokes the interpreter
with the model and sample inputs.
...
...
@@ -490,4 +490,4 @@ with the model and sample inputs.
## Train your own model
To train your own model, or create a new model for a new set of gestures,
follow the instructions in [magic_wand/train/README.md](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/magic_wand/train/README.md).
follow the instructions in [magic_wand/train/README.md](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand/train/README.md).
<atarget="_blank"href="https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb"><imgsrc="https://www.tensorflow.org/images/colab_logo_32px.png"/>Run in Google Colab</a>
<atarget="_blank"href="https://colab.research.google.com/github/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb"><imgsrc="https://www.tensorflow.org/images/colab_logo_32px.png"/>Run in Google Colab</a>
</td>
<td>
<atarget="_blank"href="https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb"><imgsrc="https://www.tensorflow.org/images/GitHub-Mark-32px.png"/>View source on GitHub</a>
<atarget="_blank"href="https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb"><imgsrc="https://www.tensorflow.org/images/GitHub-Mark-32px.png"/>View source on GitHub</a>
"This notebook demonstrates how to train a 20kb gesture recognition model for [TensorFlow Lite for Microcontrollers](https://tensorflow.org/lite/microcontrollers/overview). It will produce the same model used in the [magic_wand](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/magic_wand) example application.\n",
"This notebook demonstrates how to train a 20kb gesture recognition model for [TensorFlow Lite for Microcontrollers](https://tensorflow.org/lite/microcontrollers/overview). It will produce the same model used in the [magic_wand](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand) example application.\n",
"\n",
"The model is designed to be used with [Google Colaboratory](https://colab.research.google.com).\n",
" \u003ca target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" /\u003eRun in Google Colab\u003c/a\u003e\n",
" \u003ca target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" /\u003eRun in Google Colab\u003c/a\u003e\n",
" \u003c/td\u003e\n",
" \u003ctd\u003e\n",
" \u003ca target=\"_blank\" href=\"https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" /\u003eView source on GitHub\u003c/a\u003e\n",
" \u003ca target=\"_blank\" href=\"https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/magic_wand/train/train_magic_wand_model.ipynb\"\u003e\u003cimg src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" /\u003eView source on GitHub\u003c/a\u003e\n",
Note: Mbed has a dependency to an old version of arm_math.h and cmsis_gcc.h (adapted from the general [CMSIS-NN MBED example](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/kernels/cmsis_nn#example-2---mbed)). Therefore you need to copy the newer version as follows:
Note: Mbed has a dependency to an old version of arm_math.h and cmsis_gcc.h (adapted from the general [CMSIS-NN MBED example](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/kernels/cmsis_nn#example-2---mbed)). Therefore you need to copy the newer version as follows:
@@ -96,7 +96,7 @@ input(s) and output(s) which remain float.* -->
This is a simple model comprising of a Convolutional 2D layer, a Fully Connected
Layer or a MatMul Layer (output: logits) and a Softmax layer
(output: probabilities) as shown below. Refer to the [`tiny_conv`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/speech_commands/models.py#L673)
(output: probabilities) as shown below. Refer to the [`tiny_conv`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/examples/speech_commands/models.py#L673)
"This notebook demonstrates how to train a 20 kB [Simple Audio Recognition](https://www.tensorflow.org/tutorials/sequences/audio_recognition) model to recognize keywords in speech.\n",
"\n",
"The model created in this notebook is used in the [micro_speech](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/micro_speech) example for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview).\n",
"The model created in this notebook is used in the [micro_speech](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech) example for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview).\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" <a target=\"_blank\" href=\"https://colab.research.google.com/github/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb\"><img src=\"https://www.tensorflow.org/images/colab_logo_32px.png\" />Run in Google Colab</a>\n",
" </td>\n",
" <td>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" <a target=\"_blank\" href=\"https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb\"><img src=\"https://www.tensorflow.org/images/GitHub-Mark-32px.png\" />View source on GitHub</a>\n",
" </td>\n",
"</table>\n"
]
...
...
@@ -574,11 +574,11 @@
"source": [
"## Deploy to a Microcontroller\n",
"\n",
"Follow the instructions in the [micro_speech](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/micro_speech) README.md for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview) to deploy this model on a specific microcontroller.\n",
"Follow the instructions in the [micro_speech](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech) README.md for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview) to deploy this model on a specific microcontroller.\n",
"\n",
"**Reference Model:** If you have not modified this notebook, you can follow the instructions as is, to deploy the model. Refer to the [`micro_speech/train/models`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/train/models) directory to access the models generated in this notebook.\n",
"**Reference Model:** If you have not modified this notebook, you can follow the instructions as is, to deploy the model. Refer to the [`micro_speech/train/models`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/models) directory to access the models generated in this notebook.\n",
"\n",
"**New Model:** If you have generated a new model to identify different words: (i) Update `kCategoryCount` and `kCategoryLabels` in [`micro_speech/micro_features/micro_model_settings.h`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/micro_features/micro_model_settings.h) and (ii) Update the values assigned to the variables defined in [`micro_speech/micro_features/model.cc`](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/micro_features/model.cc) with values displayed after running the following cell."
"**New Model:** If you have generated a new model to identify different words: (i) Update `kCategoryCount` and `kCategoryLabels` in [`micro_speech/micro_features/micro_model_settings.h`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/micro_features/micro_model_settings.h) and (ii) Update the values assigned to the variables defined in [`micro_speech/micro_features/model.cc`](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/micro_features/model.cc) with values displayed after running the following cell."
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Redirect","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyO1u6oks1qPVEQNnHFD3Cyo"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"markdown","metadata":{"id":"86C-FMxpdZxv","colab_type":"text"},"source":["This Colab notebook has been moved to [https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb)\n"]}]}
\ No newline at end of file
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Redirect","provenance":[],"collapsed_sections":[],"authorship_tag":"ABX9TyO1u6oks1qPVEQNnHFD3Cyo"},"kernelspec":{"name":"python3","display_name":"Python 3"}},"cells":[{"cell_type":"markdown","metadata":{"id":"86C-FMxpdZxv","colab_type":"text"},"source":["This Colab notebook has been moved to [https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/examples/micro_speech/train/train_micro_speech_model.ipynb)\n"]}]}
@@ -5,12 +5,12 @@ This folder has been autogenerated by TensorFlow, and contains sources, headers,
This project has been generated for a target defined by TCF file only (Tool Configuration File). The real target board is unspecified, and applications can be run only in the nSIM simulator included with MWDT.
for details on how projects like this can be generated from the main source tree.
## Usage
See [Custom ARC EM/HS Platform](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/tools/make/targets/arc/README.md#Custom-ARC-EMHS-Platform) section for more detailed information on requirements and usage of this project.
See [Custom ARC EM/HS Platform](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/tools/make/targets/arc/README.md#Custom-ARC-EMHS-Platform) section for more detailed information on requirements and usage of this project.
The Makefile contains all the information on building and running the project. One can modify it to satisfy specific needs. Next actions are available out of the box. You may need to adjust the following commands in order to use the appropriate make tool available in your environment, ie: `make` or `gmake`
...
...
@@ -22,7 +22,7 @@ The Makefile contains all the information on building and running the project. O
make app EXT_CFLAGS=[additional compiler flags]
3. Build the application and stripout TFLM reference kernel fallback implementations in order to reduce code size. This only has an effect in case the project was generated with MLI support. See more info in [EmbARC MLI Library Based Optimizations](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/kernels/arc_mli/README.md). `false` is the default value.
3. Build the application and stripout TFLM reference kernel fallback implementations in order to reduce code size. This only has an effect in case the project was generated with MLI support. See more info in [EmbARC MLI Library Based Optimizations](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/kernels/arc_mli/README.md). `false` is the default value.
for details on how projects like this can be generated from the main source tree.
## Usage
See [ARC EM Software Development Platform](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/tools/make/targets/arc/README.md#ARC-EM-Software-Development-Platform-ARC-EM-SDP) section for more detailed information on requirements and usage of this project.
See [ARC EM Software Development Platform](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/tools/make/targets/arc/README.md#ARC-EM-Software-Development-Platform-ARC-EM-SDP) section for more detailed information on requirements and usage of this project.
The Makefile contains all the information on building and running the project. One can modify it to satisfy specific needs. Next actions are available out of the box. You may need to adjust the following commands in order to use the appropriate make tool available in your environment, ie: `make` or `gmake`:
...
...
@@ -22,7 +22,7 @@ The Makefile contains all the information on building and running the project. O
make app EXT_CFLAGS=[additional compiler flags]
3. Build the application and stripout TFLM reference kernel fallback implementations in order to reduce code size. This only has an effect in case the project was generated with MLI support. See more info in [EmbARC MLI Library Based Optimizations](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/kernels/arc_mli/README.md). `false` is the default value.
3. Build the application and stripout TFLM reference kernel fallback implementations in order to reduce code size. This only has an effect in case the project was generated with MLI support. See more info in [EmbARC MLI Library Based Optimizations](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/kernels/arc_mli/README.md). `false` is the default value.
make app MLI_ONLY=[true|false]
...
...
@@ -38,7 +38,7 @@ The Makefile contains all the information on building and running the project. O
make debug
7. Generate necessary artefacts for self-booting execution from flash. See [reference to Run the application on the board from the micro SD card](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/tools/make/targets/arc/README.md#Run-the-Application-on-the-Board-from-the-microSD-Card).
7. Generate necessary artefacts for self-booting execution from flash. See [reference to Run the application on the board from the micro SD card](https://github.com/tensorflow/tflite-micro/blob/main/tensorflow/lite/micro/tools/make/targets/arc/README.md#Run-the-Application-on-the-Board-from-the-microSD-Card).
