Download as PDF, PPTX
![© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "22
const float inline_Variable_2_0 [ 20 ] = {
-0.07518502, -0.094865195, -2.2947302, 2.420463, -0.39691946,
0.2372103, 1.1672685, -1.1217928, -1.3336784, 1.2321934,
-2.725729, 2.5416267, 0.8984613, -1.0757952, -0.064421736,
-0.10880947, 0.57309926, -0.8162274, -0.01253005, -0.038079493
};
Code (weight and bias)](https://image.slidesharecdn.com/utensor-embeddeddevicesandmachinelearningmodels-191007151329/75/uTensor-embedded-devices-and-machine-learning-models-22-2048.jpg)
![© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "23
Elf2Bin: XOR
| Module | .text | .data | .bss |
|--------------------|-----------------|-------------|---------------|
| [fill] | 530 | 7 | 32 |
| [lib]/c.a | 69431 | 2548 | 127 |
| [lib]/gcc.a | 7456 | 0 | 0 |
| [lib]/m.a | 788 | 0 | 0 |
| [lib]/misc | 252 | 16 | 28 |
| [lib]/nosys.a | 32 | 0 | 0 |
| [lib]/stdc++.a | 173167 | 165 | 5676 |
| main.o | 1558 | 4 | 321 |
| mbed-os/cmsis | 1033 | 0 | 0 |
| mbed-os/components | 78 | 0 | 0 |
| mbed-os/drivers | 976 | 0 | 0 |
| mbed-os/hal | 1432 | 4 | 66 |
| mbed-os/platform | 4215 | 260 | 253 |
| mbed-os/rtos | 7243 | 168 | 5973 |
| mbed-os/targets | 6709 | 4 | 364 |
| models/xor_relu.o | 23342 | 4 | 1 |
| uTensor/uTensor | 6709 | 28 | 7 |
| Subtotals | 304951 | 3208 | 12848 |
Total Static RAM memory (data + bss): 16056 bytes
Total Flash memory (text + data): 308159 bytes
Binary XOR](https://image.slidesharecdn.com/utensor-embeddeddevicesandmachinelearningmodels-191007151329/75/uTensor-embedded-devices-and-machine-learning-models-23-2048.jpg)
![© 2019 SAP SE or an SAP affiliate company. All rights reserved. ǀ "24
Elf2Bin: MNIST_LCD
| Module | .text | .data | .bss |
|----------------------------------------|---------------|-------------|---------------|
| DISCO_L476VG_GlassLCD/BSP_DISCO_L476VG | 1960 | 0 | 76 |
| DISCO_L476VG_GlassLCD/LCD_DISCO_L476VG | 34 | 0 | 0 |
| [fill] | 553 | 3 | 42 |
| [lib]/c.a | 68359 | 2548 | 127 |
| [lib]/gcc.a | 7456 | 0 | 0 |
| [lib]/m.a | 788 | 0 | 0 |
| [lib]/misc | 252 | 16 | 28 |
| [lib]/nosys.a | 32 | 0 | 0 |
| [lib]/stdc++.a | 173167 | 165 | 5676 |
| main.o | 4424 | 4 | 30 |
| mbed-os/cmsis | 1033 | 0 | 84 |
| mbed-os/components | 156 | 4 | 4 |
| mbed-os/drivers | 692 | 4 | 100 |
| mbed-os/hal | 2734 | 8 | 247 |
| mbed-os/platform | 2021 | 256 | 136 |
| mbed-os/rtos | 7678 | 168 | 6289 |
| mbed-os/targets | 12882 | 8 | 913 |
| models/deep_mlp.o | 138837 | 4 | 1 |
| uTensor/uTensor | 6709 | 28 | 7 |
| Subtotals | 429767 | 3216 | 13760 |
Total Static RAM memory (data + bss): 16976 bytes
Total Flash memory (text + data): 432983 bytes
Binary MNIST_LCD](https://image.slidesharecdn.com/utensor-embeddeddevicesandmachinelearningmodels-191007151329/75/uTensor-embedded-devices-and-machine-learning-models-24-2048.jpg)
Uploaded byLars Gregori
uTensor - embedded devices and machine learning models
The document discusses the integration of machine learning models with uTensor for embedded devices, emphasizing energy efficiency and the potential for advanced applications. It includes examples of machine learning models such as XOR and MNIST, along with their performance metrics and coding implementations. Additionally, it highlights the ongoing development of uTensor, which aims to enhance capabilities and optimize binary sizes.
More Related Content
Similar to uTensor - embedded devices and machine learning models
![[DE] AI und Minecraft](https://cdn.slidesharecdn.com/ss_thumbnails/m3minecraftandrl-180426192507-thumbnail.jpg?width=640&height=640&fit=bounds)
![[DE] IoT Protokolle](https://cdn.slidesharecdn.com/ss_thumbnails/iotcon2018iotprotokolle-180316071309-thumbnail.jpg?width=640&height=640&fit=bounds)
![[German] Boards für das IoT-Prototyping](https://cdn.slidesharecdn.com/ss_thumbnails/buildingiot2017boardsfuerdasiot-prototypinglarsgregori-170506222406-thumbnail.jpg?width=640&height=640&fit=bounds)
uTensor - embedded devices and machine learning models
- 1. Lars Gregori, SAPCX September 30, 2019 uTensor Embedded Devices And Machine Learning Models
- 2. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "2 SpeedAvailabilityPrivacy Why?
- 3. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "3 • Energy is the limiting factor • CPUs and sensors use almost no power • radios and displays use lots • We capture much more sensor data than we use Why the Future of Deep Learning is Tiny https://petewarden.com/2018/06/11/why-the-future-of-machine-learning-is-tiny/
- 4. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "4 “ML on tiny, cheap battery powered chips is coming and will open the door for some amazing new applications!” -- Pete Warden
- 7. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "7 IoT Gateway (credit: http://sappress.de/4795)
- 8.
- 9. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "9 Machine Learning Models uTensor + Code Examples Agenda
- 10.
- 11. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "11 XOR input_a input_b output 0 0 0 0 1 1 1 0 1 1 1 0
- 12. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "12 1. XOR model with Keras 2. XOR model with TensorFlow 3. MNIST model with TensorFlow Machine Learning Models https://github.com/choas/utensor_examples MNIST:
- 13.
- 14. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "14 TensorBoard - XOR model (Keras)
- 15. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "15 TensorBoard - XOR model (Keras)
- 16. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "16 step 17000, training accuracy 0.94 step 18000, training accuracy 0.94 step 19000, training accuracy 0.9 step 20000, training accuracy 0.86 test accuracy 0.9272 step 97000, training accuracy 0.97 step 98000, training accuracy 0.96 step 99000, training accuracy 1 step 100000, training accuracy 0.97 test accuracy 0.9546 MNIST training (20,000 steps and 100,000 steps) training steps don’t influence the model size size: • # layers • # nodes • value type (e.g. float, int)
- 17.
- 18. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "18 uTensor https://github.com/uTensor/uTensor
- 19. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "19 • Add • ArgMax • Dropout • MatMal • Max • Min • Placeholder • Quantization Ops • ReLu • Reshape uTensor - What is supported?
- 20. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "20 ARM Mbed OS 5 https://os.mbed.com/docs/mbed-os/v5.12/introduction/index.html
- 21. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "21 { ctx.add(new RamTensor<int>(), "y_pred:0"); ctx.push(new ArgMaxOp<float, int>(), { "add_1:0", "y_pred/dimension:0" }, { "y_pred:0" }); } Code
- 22. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "22 const float inline_Variable_2_0 [ 20 ] = { -0.07518502, -0.094865195, -2.2947302, 2.420463, -0.39691946, 0.2372103, 1.1672685, -1.1217928, -1.3336784, 1.2321934, -2.725729, 2.5416267, 0.8984613, -1.0757952, -0.064421736, -0.10880947, 0.57309926, -0.8162274, -0.01253005, -0.038079493 }; Code (weight and bias)
- 23. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "23 Elf2Bin: XOR | Module | .text | .data | .bss | |--------------------|-----------------|-------------|---------------| | [fill] | 530 | 7 | 32 | | [lib]/c.a | 69431 | 2548 | 127 | | [lib]/gcc.a | 7456 | 0 | 0 | | [lib]/m.a | 788 | 0 | 0 | | [lib]/misc | 252 | 16 | 28 | | [lib]/nosys.a | 32 | 0 | 0 | | [lib]/stdc++.a | 173167 | 165 | 5676 | | main.o | 1558 | 4 | 321 | | mbed-os/cmsis | 1033 | 0 | 0 | | mbed-os/components | 78 | 0 | 0 | | mbed-os/drivers | 976 | 0 | 0 | | mbed-os/hal | 1432 | 4 | 66 | | mbed-os/platform | 4215 | 260 | 253 | | mbed-os/rtos | 7243 | 168 | 5973 | | mbed-os/targets | 6709 | 4 | 364 | | models/xor_relu.o | 23342 | 4 | 1 | | uTensor/uTensor | 6709 | 28 | 7 | | Subtotals | 304951 | 3208 | 12848 | Total Static RAM memory (data + bss): 16056 bytes Total Flash memory (text + data): 308159 bytes Binary XOR
- 24. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "24 Elf2Bin: MNIST_LCD | Module | .text | .data | .bss | |----------------------------------------|---------------|-------------|---------------| | DISCO_L476VG_GlassLCD/BSP_DISCO_L476VG | 1960 | 0 | 76 | | DISCO_L476VG_GlassLCD/LCD_DISCO_L476VG | 34 | 0 | 0 | | [fill] | 553 | 3 | 42 | | [lib]/c.a | 68359 | 2548 | 127 | | [lib]/gcc.a | 7456 | 0 | 0 | | [lib]/m.a | 788 | 0 | 0 | | [lib]/misc | 252 | 16 | 28 | | [lib]/nosys.a | 32 | 0 | 0 | | [lib]/stdc++.a | 173167 | 165 | 5676 | | main.o | 4424 | 4 | 30 | | mbed-os/cmsis | 1033 | 0 | 84 | | mbed-os/components | 156 | 4 | 4 | | mbed-os/drivers | 692 | 4 | 100 | | mbed-os/hal | 2734 | 8 | 247 | | mbed-os/platform | 2021 | 256 | 136 | | mbed-os/rtos | 7678 | 168 | 6289 | | mbed-os/targets | 12882 | 8 | 913 | | models/deep_mlp.o | 138837 | 4 | 1 | | uTensor/uTensor | 6709 | 28 | 7 | | Subtotals | 429767 | 3216 | 13760 | Total Static RAM memory (data + bss): 16976 bytes Total Flash memory (text + data): 432983 bytes Binary MNIST_LCD
- 25.
- 27. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "27 NUCLEO-F411RE https://os.mbed.com/platforms/ST-Nucleo-F411RE/ DISCO-L476VG https://os.mbed.com/platforms/ST-Discovery-L476VG/ DISCO-F413ZH https://os.mbed.com/platforms/ST-Discovery-F413H/ Hardware
- 28.
- 29. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "29 uTensor is young and under going rapid development. Many exciting features are on the way: • Convolution • Pooling • CMSIS-NN integration (https://arm-software.github.io/CMSIS_5/NN/html/index.html) • Smaller binary • More efficient Run-time uTensor README.MD
- 30.
- 31. © 2019 SAPSE or an SAP affiliate company. All rights reserved. ǀ "31 • Why • Machine Learning Models • uTensor • C++ code • TensorFlow Lite Micro Summary
- 32.