maix.nn

maix.nn module

You can use maix.nn to access this module with MaixPy
This module is generated from MaixCDK

Module

module brief
F maix.nn.F module

Enum

Variable

Function

Class

YOLOv5

item doc
brief YOLOv5 class

C++ defination code:

class YOLOv5

__init__

item doc
type func
brief Constructor of YOLOv5 class
param model: model path, default empty, you can load model later by load function.
throw If model arg is not empty and load failed, will throw err::Exception.
static False

C++ defination code:

YOLOv5(const string &model = "")

load

item doc
type func
brief Load model from file
param model: Model path want to load
return err::Err
static False

C++ defination code:

err::Err load(const string &model)

detect

item doc
type func
brief Detect objects from image
param img: Image want to detect, if image's size not match model input's, will auto resize with fit method.
conf_th: Confidence threshold, default 0.5.
iou_th: IoU threshold, default 0.45.
fit: Resize method, default image.Fit.FIT_CONTAIN.
throw If image format not match model input format, will throw err::Exception.
return Object list. In C++, you should delete it after use.
static False

C++ defination code:

std::vector<nn::Object> *detect(image::Image &img, float conf_th = 0.5, float iou_th = 0.45, maix::image::Fit fit = maix::image::FIT_CONTAIN)

input_size

item doc
type func
brief Get model input size
return model input size
static False

C++ defination code:

image::Size input_size()

input_width

item doc
type func
brief Get model input width
return model input size of width
static False

C++ defination code:

int input_width()

input_height

item doc
type func
brief Get model input height
return model input size of height
static False

C++ defination code:

int input_height()

input_format

item doc
type func
brief Get input image format
return input image format, image::Format type.
static False

C++ defination code:

image::Format input_format()

labels

item doc
type var
brief Labels list
static False
readonly False

C++ defination code:

std::vector<string> labels

label_path

item doc
type var
brief Label file path
static False
readonly False

C++ defination code:

std::string label_path

mean

item doc
type var
brief Get mean value, list type
static False
readonly False

C++ defination code:

std::vector<float> mean

scale

item doc
type var
brief Get scale value, list type
static False
readonly False

C++ defination code:

std::vector<float> scale

anchors

item doc
type var
brief Get anchors
static False
readonly False

C++ defination code:

std::vector<float> anchors

Classifier

item doc
brief Classifier

C++ defination code:

class Classifier

__init__

item doc
type func
brief Construct a new Classifier object
param model: MUD model path, if empty, will not load model, you can call load() later.
if not empty, will load model and will raise err::Exception if load failed.
static False

C++ defination code:

Classifier(const string &model = "")

load

item doc
type func
brief Load model from file, model format is .mud,\nMUD file should contain [extra] section, have key-values:\n- model_type: classifier\n- input_type: rgb or bgr\n- mean: 123.675, 116.28, 103.53\n- scale: 0.017124753831663668, 0.01750700280112045, 0.017429193899782137\n- labels: imagenet_classes.txt
param model: MUD model path
return error code, if load failed, return error code
static False

C++ defination code:

err::Err load(const string &model)

classify

item doc
type func
brief Forward image to model, get result. Only for image input, use classify_raw for tensor input.
param img: image, format should match model input_type， or will raise err.Exception
softmax: if true, will do softmax to result, or will return raw value
throw If error occurred, will raise err::Exception, you can find reason in log, mostly caused by args error or hardware error.
return result, a list of (label, score). In C++, you need to delete it after use.
static False

C++ defination code:

std::vector<std::pair<int, float>> *classify(image::Image &img, bool softmax = true)

classify_raw

item doc
type func
brief Forward tensor data to model, get result
param data: tensor data, format should match model input_type， or will raise err.Excetion
softmax: if true, will do softmax to result, or will return raw value
throw If error occurred, will raise err::Exception, you can find reason in log, mostly caused by args error or hardware error.
return result, a list of (label, score). In C++, you need to delete it after use.
static False

C++ defination code:

std::vector<std::pair<int, float>> *classify_raw(tensor::Tensor &data, bool softmax = true)

input_size

item doc
type func
brief Get model input size, only for image input
return model input size
static False

C++ defination code:

image::Size input_size()

input_width

item doc
type func
brief Get model input width, only for image input
return model input size of width
static False

C++ defination code:

int input_width()

input_height

item doc
type func
brief Get model input height, only for image input
return model input size of height
static False

C++ defination code:

int input_height()

input_format

item doc
type func
brief Get input image format, only for image input
return input image format, image::Format type.
static False

C++ defination code:

image::Format input_format()

input_shape

item doc
type func
brief Get input shape, if have multiple input, only return first input shape
return input shape, list type
static False

C++ defination code:

std::vector<int> input_shape()

labels

item doc
type var
brief Labels list
static False
readonly False

C++ defination code:

std::vector<string> labels

label_path

item doc
type var
brief Label file path
static False
readonly False

C++ defination code:

std::string label_path

mean

item doc
type var
brief Get mean value, list type
static False
readonly False

C++ defination code:

std::vector<float> mean

scale

item doc
type var
brief Get scale value, list type
static False
readonly False

C++ defination code:

std::vector<float> scale

MUD

item doc
brief MUD(model universal describe file) class

C++ defination code:

class MUD

__init__

item doc
type func
brief MUD constructor
param model_path: direction [in], model file path, model format can be MUD(model universal describe file) file.
If model_path set, will load model from file, load failed will raise err.Exception.
If model_path not set, you can load model later by load function.
static False

C++ defination code:

MUD(const char *model_path = nullptr)

load

item doc
type func
brief Load model from file
param model_path: direction [in], model file path, model format can be MUD(model universal describe file) file.
return error code, if load success, return err::ERR_NONE
static False

C++ defination code:

err::Err load(const std::string &model_path)

type

item doc
type var
brief Model type, string type
static False
readonly False

C++ defination code:

std::string type

items

item doc
type var
brief Model config items, different model type has different config items
static False
readonly False

C++ defination code:

std::map<std::string, std::map<std::string, std::string>> items

LayerInfo

item doc
brief NN model layer info

C++ defination code:

class LayerInfo

__init__

item doc
type func
brief LayerInfo constructor
param name: direction [in], layer name
dtype: direction [in], layer data type
shape: direction [in], layer shape
static False

C++ defination code:

LayerInfo(const std::string &name =  "", tensor::DType dtype = tensor::DType::FLOAT32, std::vector<int> shape = std::vector<int>())

name

item doc
type var
brief Layer name
static False
readonly False

C++ defination code:

std::string   name

dtype

item doc
type var
brief Layer data type
attention If model is quantized, this is the real quantized data type like int8 float16,
in most scene, inputs and outputs we actually use float32 in API like forward.
static False
readonly False

C++ defination code:

tensor::DType dtype

shape

item doc
type var
brief Layer shape
static False
readonly False

C++ defination code:

std::vector<int> shape

to_str

item doc
type func
brief To string
static False

C++ defination code:

std::string to_str()

__str__

item doc
type func
brief To string
static False

C++ defination code:

std::string __str__()

NN

item doc
brief Neural network class

C++ defination code:

class NN

__init__

item doc
type func
brief Neural network constructor
param model: direction [in], model file path, model format can be MUD(model universal describe file) file.
If model_path set, will load model from file, load failed will raise err.Exception.
If model_path not set, you can load model later by load function.
static False

C++ defination code:

NN(const std::string &model = "")

load

item doc
type func
brief Load model from file
param model: direction [in], model file path, model format can be MUD(model universal describe file) file.
return error code, if load success, return err::ERR_NONE
static False

C++ defination code:

err::Err load(const std::string &model)

loaded

item doc
type func
brief Is model loaded
return true if model loaded, else false
static False

C++ defination code:

bool loaded()

inputs_info

item doc
type func
brief Get model input layer info
return input layer info
static False

C++ defination code:

std::vector<nn::LayerInfo> inputs_info()

outputs_info

item doc
type func
brief Get model output layer info
return output layer info
static False

C++ defination code:

std::vector<nn::LayerInfo> outputs_info()

extra_info

item doc
type func
brief Get model extra info define in MUD file
return extra info, dict type, key-value object, attention: key and value are all string type.
static False

C++ defination code:

std::map<std::string, std::string> extra_info()

forward

item doc
type func
brief forward run model, get output of model,\nthis is specially for MaixPy, not efficient, but easy to use in MaixPy
param input: direction [in], input tensor
return output tensor. In C++, you should manually delete tensors in return value and return value.
static False

C++ defination code:

tensor::Tensors *forward(tensor::Tensors &inputs)

forward_image

item doc
type func
brief forward model, param is image
param img: input image
mean: mean value, a list type, e.g. [0.485, 0.456, 0.406], default is empty list means not normalize.
scale: scale value, a list type, e.g. [1/0.229, 1/0.224, 1/0.225], default is empty list means not normalize.
fit: fit mode, if the image size of input not equal to model's input, it will auto resize use this fit method,
default is image.Fit.FIT_FILL for easy coordinate calculation, but for more accurate result, use image.Fit.FIT_CONTAIN is better.
copy_result: If set true, will copy result to a new variable; else will use a internal memory, you can only use it until to the next forward.
Default true to avoid problems, you can set it to false manually to make speed faster.
return output tensor. In C++, you should manually delete tensors in return value and return value.
static False

C++ defination code:

tensor::Tensors *forward_image(image::Image &img, std::vector<float> mean = std::vector<float>(), std::vector<float> scale = std::vector<float>(), image::Fit fit = image::Fit::FIT_FILL, bool copy_result = true)

Object

item doc
brief Object for detect result

C++ defination code:

class Object

__init__

item doc
type func
brief Constructor of Object for detect result
param x: left top x
y: left top y
w: width
h: height
class_id: class id
score: score
static False

C++ defination code:

Object(int x = 0, int y = 0, int w = 0, int h = 0, int class_id = 0, float score = 0)

__str__

item doc
type func
brief Object info to string
return Object info string
static False

C++ defination code:

std::string to_str()

x

item doc
type var
brief Object left top coordinate x
static False
readonly False

C++ defination code:

int x

y

item doc
type var
brief Object left top coordinate y
static False
readonly False

C++ defination code:

int y

w

item doc
type var
brief Object width
static False
readonly False

C++ defination code:

int w

h

item doc
type var
brief Object height
static False
readonly False

C++ defination code:

int h

class_id

item doc
type var
brief Object class id
static False
readonly False

C++ defination code:

int class_id

score

item doc
type var
brief Object score
static False
readonly False

C++ defination code:

float score