models/human_segmentation_pphumanseg/pphumanseg.py

# This file is part of OpenCV Zoo project.
# It is subject to the license terms in the LICENSE file found in the same directory.
#
# Copyright (C) 2021, Shenzhen Institute of Artificial Intelligence and Robotics for Society, all rights reserved.
# Third party copyrights are property of their respective owners.

import numpy as np
import cv2 as cv

class PPHumanSeg:
    def __init__(self, modelPath, backendId=0, targetId=0):
        self._modelPath = modelPath
        self._backendId = backendId
        self._targetId = targetId

        self._model = cv.dnn.readNet(self._modelPath)
        self._model.setPreferableBackend(self._backendId)
        self._model.setPreferableTarget(self._targetId)

        self._inputNames = ''
        self._outputNames = ['save_infer_model/scale_0.tmp_1']
        self._currentInputSize = None
        self._inputSize = [192, 192]
        self._mean = np.array([0.5, 0.5, 0.5])[np.newaxis, np.newaxis, :]
        self._std = np.array([0.5, 0.5, 0.5])[np.newaxis, np.newaxis, :]

    @property
    def name(self):
        return self.__class__.__name__

    def setBackendAndTarget(self, backendId, targetId):
        self._backendId = backendId
        self._targetId = targetId
        self._model.setPreferableBackend(self._backendId)
        self._model.setPreferableTarget(self._targetId)

    def _preprocess(self, image):

        image = cv.cvtColor(image, cv.COLOR_BGR2RGB)

        self._currentInputSize = image.shape
        image = cv.resize(image, (192, 192))
        
        image = image.astype(np.float32, copy=False) / 255.0
        image -= self._mean
        image /= self._std
        return cv.dnn.blobFromImage(image)

    def infer(self, image):

        # Preprocess
        inputBlob = self._preprocess(image)

        # Forward
        self._model.setInput(inputBlob, self._inputNames)
        outputBlob = self._model.forward()

        # Postprocess
        results = self._postprocess(outputBlob)

        return results

    def _postprocess(self, outputBlob):
        
        outputBlob = outputBlob[0]
        outputBlob = cv.resize(outputBlob.transpose(1,2,0), (self._currentInputSize[1], self._currentInputSize[0]), interpolation=cv.INTER_LINEAR).transpose(2,0,1)[np.newaxis, ...]

        result = np.argmax(outputBlob, axis=1).astype(np.uint8)
        return result