vitis::ai::Hourglass

Hourglass model, input size is 256x256.

Base class for detecting poses of people.

Input is an image (cv:Mat).

Output is HourglassResult.

Sample code:

auto image = cv::imread(argv[2]);
if (image.empty()) {
  std::cerr << "cannot load " << argv[2] << std::endl;
  abort();
}
auto det = vitis::ai::Hourglass::create(argv[1]);
vector<vector<int>> limbSeq = {{0, 1},  {1, 2},   {2, 6},  {3, 6},  {3, 4}, {4, 5},
                               {6, 7},   {7, 8},  {8, 9}, {7, 12},
                               {12, 11}, {11, 10}, {7, 13}, {13, 14}, {14, 15}};

auto results = det->run(image.clone());
for (size_t i = 0; i < results.poses.size(); ++i) {
  cout<< results.poses[i].point<<endl;
  if (results.poses[i].type == 1) {
    cv::circle(image, results.poses[i].point, 5, cv::Scalar(0, 255, 0),
               -1);
  }
}
for (size_t i = 0; i < limbSeq.size(); ++i) {
  Result a = results.poses[limbSeq[i][0]];
  Result b = results.poses[limbSeq[i][1]];
  if (a.type == 1 && b.type == 1) {
    cv::line(image, a.point, b.point, cv::Scalar(255, 0, 0), 3, 4);
  }
}

Display of the hourglass model results:

Image sample_hourglass_result.jpg — Figure 1: hourglass result image

Quick Function Reference

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

Table 1. Quick Function Reference
Type	Name	Arguments
std::unique_ptr< `Hourglass` >	create	const std::string & model_name bool need_preprocess
`HourglassResult`	run	const cv::Mat & image
std::vector< `HourglassResult` >	run	const std::vector< cv::Mat > & images
int	getInputWidth	void
int	getInputHeight	void
size_t	get_input_batch	void

create

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

Prototype

std::unique_ptr< Hourglass > 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 Hourglass class.

run

Function to get running result of the hourglass neuron network.

Prototype


            HourglassResult 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

HourglassResult.

run

Function to get running results of the hourglass neuron network in batch mode.

Prototype

std::vector< HourglassResult > 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 batch input images (vector<cv::Mat>). The size of input images equals batch size obtained by get_input_batch.

Returns

The vector of HourglassResult.

getInputWidth

Function to get InputWidth of the hourglass network (input image columns).

Prototype

int getInputWidth() const =0;

Returns

InputWidth of the hourglass network

getInputHeight

Function to get InputHeight of the hourglass network (input image rows).

Prototype

int getInputHeight() const =0;

Returns

InputHeight of the hourglass network.

get_input_batch

Function to get the number of images processed by the DPU at one time.

Note: Different DPU core the batch size may be different. This depends on the IP used.

Prototype

size_t get_input_batch() const =0;

Returns

Batch size.