TinyML
来自Jack's Lab
（版本间的差异）
(→Quick Start) |
(→Overview) |
||
| （未显示1个用户的10个中间版本） | |||
| 第3行： | 第3行： | ||
* [https://eloquentarduino.github.io/2020/01/easy-tinyml-on-esp32-and-arduino/ Easy Tensorflow TinyML on ESP32 and Arduino] | * [https://eloquentarduino.github.io/2020/01/easy-tinyml-on-esp32-and-arduino/ Easy Tensorflow TinyML on ESP32 and Arduino] | ||
* z-lib.org | * z-lib.org | ||
| + | |||
| + | |||
| + | |||
| + | TinyML 基金会在 2019 年组织了第一届峰会，这届峰会的成果如下： | ||
| + | |||
| + | * TinyML 的技术硬件已经进入了实用性的阶段； | ||
| + | * 算法，网络以及低于 100KB 的 ML 模型，已经取得重大突破； | ||
| + | * 视觉，音频的低功耗需求快速增长。 | ||
<br><br> | <br><br> | ||
| + | |||
| + | == Hardware == | ||
| + | |||
| + | * Sparkfunc Edge: | ||
| + | ** Cortex-M4F up to 48MHz, 6uA/MHz (Ambiq Micro Apollo3 Blue) https://ambiq.com/apollo3-blue-datasheet/ | ||
| + | ** 1MB Flash, 384KB RAM | ||
| + | |||
| + | |||
| + | * Arduino Nano 33 BLE Sense [https://docs.arduino.cc/static/5ae03c9567ffd89ec14cfc856a5d58a2/ABX00031-datasheet.pdf Nano 33 Datasheet] | ||
| + | ** Cortex-M4F, up to 64MHz, 52 µA/MHz (Nordic nRF52480) https://content.arduino.cc/assets/Nano_BLE_MCU-nRF52840_PS_v1.1.pdf | ||
| + | ** 1 MB Flash, 256 kB RAM | ||
| + | |||
| + | |||
| + | * [https://www.st.com/en/evaluation-tools/32f746gdiscovery.html STM32F746G Discovery Kit] | ||
| + | ** Cortex®-M7 up to 216MHz [https://www.st.com/resource/en/datasheet/stm32f746ng.pdf STM32F746G DS] | ||
| + | ** 1 MB Flash, 320KB RAM | ||
| + | ** LQFP100 (14x14 mm), TFBGA100 (8x8 mm), WLCSP143 (4.5x5.8 mm) | ||
| + | |||
| + | <br> | ||
== Quick Start == | == Quick Start == | ||
<source lang=bash> | <source lang=bash> | ||
| − | $ pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow-gpu==2. | + | $ pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow-gpu==2.5.0 |
$ python3 | $ python3 | ||
import tensorflow as tf | import tensorflow as tf | ||
| − | hello = tf.constant('Hello, | + | >>> print(tf.__version__) |
| − | print(hello) | + | 2.5.0 |
| − | + | ||
| − | Hello, | + | >>> print('GPU: ', tf.test.is_gpu_available()) |
| + | 2022-04-01 03:24:13.099644: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: | ||
| + | pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1050 computeCapability: 6.1 | ||
| + | coreClock: 1.493GHz coreCount: 5 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 104.43GiB/s | ||
| + | 2022-04-01 03:24:13.099980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0 | ||
| + | 2022-04-01 03:24:13.100248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix: | ||
| + | 2022-04-01 03:24:13.100459: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0 | ||
| + | 2022-04-01 03:24:13.100669: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N | ||
| + | 2022-04-01 03:24:13.100967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/device:GPU:0 with 2779 MB memory) -> physical G | ||
| + | PU (device: 0, name: NVIDIA GeForce GTX 1050, pci bus id: 0000:01:00.0, compute capability: 6.1) | ||
| + | GPU: True | ||
| + | |||
| + | >>> hello = tf.constant('Hello, Tensorflow!') | ||
| + | >>> print(hello) | ||
| + | tf.Tensor(b'Hello, Tensorflow!', shape=(), dtype=string) | ||
| + | |||
| + | >>> from tensorflow.python.client import device_lib | ||
| + | >>> print(device_lib.list_local_devices()) | ||
| + | [name: "/device:CPU:0" | ||
| + | device_type: "CPU" | ||
| + | memory_limit: 268435456 | ||
| + | locality { | ||
| + | } | ||
| + | incarnation: 12041451716771642396 | ||
| + | , name: "/device:GPU:0" | ||
| + | device_type: "GPU" | ||
| + | memory_limit: 2914163099 | ||
| + | locality { | ||
| + | bus_id: 1 | ||
| + | links { | ||
| + | } | ||
| + | } | ||
| + | incarnation: 596105631149220834 | ||
| + | physical_device_desc: "device: 0, name: NVIDIA GeForce GTX 1050, pci bus id: 0000:01:00.0, compute capability: 6.1" | ||
| + | ] | ||
</source> | </source> | ||
<br><br> | <br><br> | ||
2022年4月14日 (四) 15:45的最后版本
[编辑] 1 Overview
TinyML 基金会在 2019 年组织了第一届峰会，这届峰会的成果如下：
- TinyML 的技术硬件已经进入了实用性的阶段；
- 算法，网络以及低于 100KB 的 ML 模型，已经取得重大突破；
- 视觉，音频的低功耗需求快速增长。
[编辑] 2 Hardware
- Sparkfunc Edge:
- Cortex-M4F up to 48MHz, 6uA/MHz (Ambiq Micro Apollo3 Blue) https://ambiq.com/apollo3-blue-datasheet/
- 1MB Flash, 384KB RAM
- Arduino Nano 33 BLE Sense Nano 33 Datasheet
- Cortex-M4F, up to 64MHz, 52 µA/MHz (Nordic nRF52480) https://content.arduino.cc/assets/Nano_BLE_MCU-nRF52840_PS_v1.1.pdf
- 1 MB Flash, 256 kB RAM
- STM32F746G Discovery Kit
- Cortex®-M7 up to 216MHz STM32F746G DS
- 1 MB Flash, 320KB RAM
- LQFP100 (14x14 mm), TFBGA100 (8x8 mm), WLCSP143 (4.5x5.8 mm)
[编辑] 3 Quick Start
$ pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple tensorflow-gpu==2.5.0
$ python3
import tensorflow as tf
>>> print(tf.__version__)
2.5.0
>>> print('GPU: ', tf.test.is_gpu_available())
2022-04-01 03:24:13.099644: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties:
pciBusID: 0000:01:00.0 name: NVIDIA GeForce GTX 1050 computeCapability: 6.1
coreClock: 1.493GHz coreCount: 5 deviceMemorySize: 4.00GiB deviceMemoryBandwidth: 104.43GiB/s
2022-04-01 03:24:13.099980: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1871] Adding visible gpu devices: 0
2022-04-01 03:24:13.100248: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix:
2022-04-01 03:24:13.100459: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0
2022-04-01 03:24:13.100669: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N
2022-04-01 03:24:13.100967: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1418] Created TensorFlow device (/device:GPU:0 with 2779 MB memory) -> physical G
PU (device: 0, name: NVIDIA GeForce GTX 1050, pci bus id: 0000:01:00.0, compute capability: 6.1)
GPU: True
>>> hello = tf.constant('Hello, Tensorflow!')
>>> print(hello)
tf.Tensor(b'Hello, Tensorflow!', shape=(), dtype=string)
>>> from tensorflow.python.client import device_lib
>>> print(device_lib.list_local_devices())
[name: "/device:CPU:0"
device_type: "CPU"
memory_limit: 268435456
locality {
}
incarnation: 12041451716771642396
, name: "/device:GPU:0"
device_type: "GPU"
memory_limit: 2914163099
locality {
bus_id: 1
links {
}
}
incarnation: 596105631149220834
physical_device_desc: "device: 0, name: NVIDIA GeForce GTX 1050, pci bus id: 0000:01:00.0, compute capability: 6.1"
]
