Comments (8)
Hi, @PureHing
Thank you for your attention.
- Yes, ESP32-S2 can also run NN functionally. However, as ESP32-S2 has no instruction boost, it is slower than ESP32-S3.
- For ESP32, ESP32-S2 and ESP32-C3 are base on ESP-IDF/release/v4.3. For ESP32-S3, the corresponding ESP-IDF is not released yet. Once ESP-IDF supports ESP32-S3, ESP-DL will be released officially.
Probably you can try ESP-DL/tutorial or ESP-DL/examples first, with ESP32, ESP32-S2, and ESP32-C3.
Best regards.
from esp-dl.
@yehangyang
Okay. Thanks much.
If the input is 480x480x1 , similar to the feature extraction of mobilenet, is the speed acceptable with esp32s3?
BTW, the master branch with 8e3e65a47b of esp-idf is suitable?
from esp-dl.
Hi, @PureHing
I think it depends on your application latency requirement.
Well, please try it with the tutorial for testing whether ESP-IDF is suitable.
Best regards.
from esp-dl.
Hi, @PureHing
I think it depends on your application latency requirement.
Well, please try it with the tutorial for testing whether ESP-IDF is suitable.Best regards.
@yehangyang
Hi,this is description on esp32s2 with human face keypoint detect
MNIST::forward: 797270 us
[0] score: 0.987729, box: [137, 75, 246, 215]
left eye: (157, 131), right eye: (158, 177)
nose: (170, 163)
mouth left: (199, 133), mouth right: (193, 180)
This is a great job!
Can you give me an overview of the network structure?
What is the maximum number of net channels in your work.
from esp-dl.
Hi, @PureHing
Thanks.
But, I'm afraid we can not tell the details of the network structure.
Best regards.
from esp-dl.
@yehangyang
Hi,
I have a question for you,according to "output_exponent" is effective for "bias" coefficient converting only by now.
,
that's means the value of each out_exponent=log2(max(abs(np.load(f'{filename}'_bias.npy))) / 2 ^ (element_width - 1)) in config.json.Is it right?
And About Bit Quantize is an empty document.
from esp-dl.
Hi, @PureHing
It because bias_exponent must equal output_exponent, so I merge them together to output_exponent.
No, output_exponent is got by yourself. You can get it by equation, output_exponent = log2(max(abs(output_float))) / 2 ^ (element_width - 1)), the output_float is the output of a layer in floating-point. Or, through other quantization method to settle the output_exponent.
And output_exponent is setted in Layer initialization, for example in tutorial.
We plan to generate a Model from the JSON file in the future. So I reserve "output_exponent" in config.json. Probably some misleading here.
We're working on writing About Bit Quantize. Briefly, all quantization(int16 and int8) follow the equation, value_float = value_quant ^ exponent. There is some difference between int16 and int8, which will be released soon. By now, you could use int16, which is much more stable.
Best regards.
from esp-dl.
Okay.Thanks
from esp-dl.
Related Issues (20)
- autotvm:Cannot find tuning records for: target=c -keys=cpu -model=esp32 (AIV-653) HOT 7
- Problem with PSRAM in the tutotial/convert_tool_example with esp32-S3-DevKitC-1 (AIV-655) HOT 1
- Color Detector model's Size bias issue (AIV-657) HOT 4
- Allow using esp-dl with esp-idf v5.1 and newer (AIV-658) HOT 2
- 报错version `GLIBC_2.27' not found (AIV-659) HOT 1
- add 'Constant' operation (AIV-666)
- tvm_example 目录下 scrip.sh脚本生成的newproject 编译成功 但下载到板子里运行报错 (AIV-668)
- How to save face ID to sdcard instead of flash (AIV-669)
- Evalutor only supports esp32s3? (AIV-671) HOT 1
- ESP-DL TVM: UnboundLocalError: local variable 'bias_add' referenced before assignment (AIV-674) HOT 1
- ESP-DL Quant Tool | TVM conversion & deployment on ESP32S3-EYE (AIV-675) HOT 2
- ESP-DL tutorial/tvm_example No module named 'tvm.relay.op.contrib.esp' (IDFGH-12113) (AIV-678) HOT 4
- ESP32 Model Deployment Project using TVM (AIV-682) HOT 14
- Face recognition: enrolled face not persisting in Arduino IDE (AIV-683)
- custom model with TVM deployment error function 'TVMGetLastPythonError' not found (AIV-685)
- Question about memory usage of models that are build with the ESP-DL Quantization Tool (AIV-686) HOT 1
- Get Started link in the Readme is not working (AIV-688) HOT 2
- Latency of Face Recognition (AIV-689) HOT 2
- Movement detection (AIV-691)
- 参照官方提供的使用 ESP-DL 深度学习库基于 ESP32-S3 实现手势识别的这篇文章中在2.3评估里使用了里面的代码但是报错(前面完全按照示例走) (AIV-693) HOT 9
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from esp-dl.