vitis::ai::Reid

Base class for getting feat from an image (cv::Mat).

Input is an image (cv::Mat).

Output image reid feat.

Sample code:

if(argc < 3){
    cerr<<"need two images"<<endl;
    return -1;
}
Mat imgx = imread(argv[1]);
if(imgx.empty()){
    cerr<<"can't load image! "<<argv[1]<<endl;
    return -1;
}
Mat imgy = imread(argv[2]);
if(imgy.empty()){
    cerr<<"can't load image! "<<argv[2]<<endl;
    return -1;
}
auto det = vitis::ai::Reid::create("reid");
Mat featx = det->run(imgx).feat;
Mat featy = det->run(imgy).feat;
double dismat= cosine_distance(featx, featy);
printf("dismat : %.3lf \n", dismat);

Quick Function Reference

The following table lists all the functions defined in the vitis::ai::Reid class:

Table 1. Quick Function Reference
Type	Name	Arguments
std::unique_ptr< `Reid` >	create	const std::string & model_name bool need_preprocess
`ReidResult`	run	const cv::Mat & image
std::vector< `ReidResult` >	run	const std::vector< cv::Mat > & images
std::vector< `ReidResult` >	run	const std::vector< vart::xrt_bo_t > & input_bos

create

Factory function to get an instance of derived classes of class Reid.

Prototype

std::unique_ptr< Reid > create(const std::string &model_name, bool need_preprocess=true);

Parameters

The following table lists the create function arguments.

Table 2. create Arguments
Type	Name	Description
const std::string &	model_name	Model name
bool	need_preprocess	Normalize with mean/scale or not, default value is true.

Returns

An instance of Reid class.

run

Function to get running result of the ReID neuron network.

Prototype


            ReidResult run(const cv::Mat &image)=0;

Parameters

The following table lists the run function arguments.

Table 3. run Arguments
Type	Name	Description
const cv::Mat &	image	Input data of input image (cv::Mat).

Returns

ReidResult.

run

Function to get running result of the ReID neuron network in batch mode.

Prototype

std::vector< ReidResult > run(const std::vector< cv::Mat > &images)=0;

Parameters

The following table lists the run function arguments.

Table 4. run Arguments
Type	Name	Description
const std::vector< cv::Mat > &	images	Input data of input images (vector<cv::Mat>).

Returns

vector of ReidResult.

run

Function to get running results of the reid neuron network in batch mode , used to receive user's xrt_bo to support zero copy.

Prototype

std::vector< ReidResult > run(const std::vector< vart::xrt_bo_t > &input_bos)=0;

Parameters

The following table lists the run function arguments.

Table 5. run Arguments
Type	Name	Description
const std::vector< vart::xrt_bo_t > &	input_bos	The vector of vart::xrt_bo_t.

Returns

The vector of ReidResult.