Contents
emlearn-micropython
Status
Features
Examples
Documentation
Citations
Developing
User Guide
1. Getting started on PC (Linux/MacOS/Windows)
1.1. Prerequisites
1.2. Install scikit-learn
1.3. Install emlearn
1.4. Install MicroPython Unix port
1.5. Install emlearn-micropython modules
1.6. Create model in Python
1.7. Use in MicroPython code
1.8. Try it out
1.9. Next
2. Getting started on device (ESP32/RP2/STM32/etc)
2.1. Prerequisites
2.2. Install mpremote
2.3. Install emlearn-micropython modules
2.4. Create model in Python
2.5. Use in MicroPython code
2.6. Try it out
2.7. Next
3. Getting started for browser
3.1. Prerequisites
3.2. emlearn-micropython build for browser
3.3. Setup web page
3.4. Try it out
3.5. Serving from device
4. Supported versions
4.1. Supported MicroPython versions
4.2. Supported hardware
5. Native modules
5.1. Supported versions
5.2. Prebuilt native modules
5.3. Installing using mip
6. External modules
6.1. Supported versions
6.2. Prerequisites
6.3. Include external modules in build
Examples
Soundlevel using IIR filters (soundlevel_iir)
Human Activity Detection using classification trees (har_trees)
Digits recognition using Convolutional Neural Networks (mnist_cnn)
XOR classification using trees (xor_trees)
API reference
emlearn_trees - Decision tree ensembles
Model
load_model()
new()
emlearn_linreg - Linear regression
Model
new()
train()
emlearn_cnn - Convolutional Neural Networks
Model
new()
emlearn_neighbors - K Nearest Neighbors (KNN)
Model
new()
emlearn_fft - Fast Fourier Transform
FFT
fill()
emlearn_iir - Infinite Impulse Reponse filters
IIR
new()
emlearn_arrayutils - Efficient utilities for array.array
linear_map()
More
emlearn documentation
Presentations
Microcontrollers + Machine Learning in 1-2-3
MicroPython - Python for microcontrollers and embedded linux
Sensor data processing on microcontrollers with MicroPython and emlearn
Machine Learning on microcontrollers using MicroPython and emlearn
Other resources
The MIT License
emlearn-micropython
Index
Index
A
|
E
|
F
|
G
|
I
|
L
|
M
|
N
|
O
|
P
|
R
|
S
|
T
A
additem() (emlearn_neighbors.Model method)
addleaf() (emlearn_trees.Model method)
addnode() (emlearn_trees.Model method)
addroot() (emlearn_trees.Model method)
E
emlearn_arrayutils
module
emlearn_cnn
module
emlearn_fft
module
emlearn_iir
module
emlearn_linreg
module
emlearn_neighbors
module
emlearn_trees
module
F
FFT (class in emlearn_fft)
fill() (emlearn_fft.FFT method)
(in module emlearn_fft)
G
get_bias() (emlearn_linreg.Model method)
get_n_features() (emlearn_linreg.Model method)
get_weights() (emlearn_linreg.Model method)
getitem() (emlearn_neighbors.Model method)
getresult() (emlearn_neighbors.Model method)
I
IIR (class in emlearn_iir)
L
linear_map() (in module emlearn_arrayutils)
load_model() (in module emlearn_trees)
M
Model (class in emlearn_cnn)
(class in emlearn_linreg)
(class in emlearn_neighbors)
(class in emlearn_trees)
module
emlearn_arrayutils
emlearn_cnn
emlearn_fft
emlearn_iir
emlearn_linreg
emlearn_neighbors
emlearn_trees
N
new() (in module emlearn_cnn)
(in module emlearn_iir)
(in module emlearn_linreg)
(in module emlearn_neighbors)
(in module emlearn_trees)
O
output_dimensions() (emlearn_cnn.Model method)
outputs() (emlearn_trees.Model method)
P
predict() (emlearn_linreg.Model method)
(emlearn_neighbors.Model method)
(emlearn_trees.Model method)
R
run() (emlearn_cnn.Model method)
(emlearn_fft.FFT method)
(emlearn_iir.IIR method)
S
score_mse() (emlearn_linreg.Model method)
set_bias() (emlearn_linreg.Model method)
set_weights() (emlearn_linreg.Model method)
setdata() (emlearn_trees.Model method)
step() (emlearn_linreg.Model method)
T
train() (in module emlearn_linreg)