Wan2GP/preprocessing/dwpose/wholebody.py

# -*- coding: utf-8 -*-
# Copyright (c) Alibaba, Inc. and its affiliates.
import cv2
import numpy as np
import onnxruntime as ort
from .onnxdet import inference_detector
from .onnxpose import inference_pose

def HWC3(x):
    assert x.dtype == np.uint8
    if x.ndim == 2:
        x = x[:, :, None]
    assert x.ndim == 3
    H, W, C = x.shape
    assert C == 1 or C == 3 or C == 4
    if C == 3:
        return x
    if C == 1:
        return np.concatenate([x, x, x], axis=2)
    if C == 4:
        color = x[:, :, 0:3].astype(np.float32)
        alpha = x[:, :, 3:4].astype(np.float32) / 255.0
        y = color * alpha + 255.0 * (1.0 - alpha)
        y = y.clip(0, 255).astype(np.uint8)
        return y


def resize_image(input_image, resolution):
    H, W, C = input_image.shape
    H = float(H)
    W = float(W)
    k = float(resolution) / min(H, W)
    H *= k
    W *= k
    H = int(np.round(H / 64.0)) * 64
    W = int(np.round(W / 64.0)) * 64
    img = cv2.resize(input_image, (W, H), interpolation=cv2.INTER_LANCZOS4 if k > 1 else cv2.INTER_AREA)
    return img

class Wholebody:
    def __init__(self, onnx_det, onnx_pose, device = 'cuda:0'):

        providers = ['CPUExecutionProvider'
                 ] if device == 'cpu' else ['CUDAExecutionProvider']
        # onnx_det = 'annotator/ckpts/yolox_l.onnx'
        # onnx_pose = 'annotator/ckpts/dw-ll_ucoco_384.onnx'

        self.session_det = ort.InferenceSession(path_or_bytes=onnx_det, providers=providers)
        self.session_pose = ort.InferenceSession(path_or_bytes=onnx_pose, providers=providers)
    
    def __call__(self, ori_img):
        det_result = inference_detector(self.session_det, ori_img)
        keypoints, scores = inference_pose(self.session_pose, det_result, ori_img)

        keypoints_info = np.concatenate(
            (keypoints, scores[..., None]), axis=-1)
        # compute neck joint
        neck = np.mean(keypoints_info[:, [5, 6]], axis=1)
        # neck score when visualizing pred
        neck[:, 2:4] = np.logical_and(
            keypoints_info[:, 5, 2:4] > 0.3,
            keypoints_info[:, 6, 2:4] > 0.3).astype(int)
        new_keypoints_info = np.insert(
            keypoints_info, 17, neck, axis=1)
        mmpose_idx = [
            17, 6, 8, 10, 7, 9, 12, 14, 16, 13, 15, 2, 1, 4, 3
        ]
        openpose_idx = [
            1, 2, 3, 4, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17
        ]
        new_keypoints_info[:, openpose_idx] = \
            new_keypoints_info[:, mmpose_idx]
        keypoints_info = new_keypoints_info

        keypoints, scores = keypoints_info[
            ..., :2], keypoints_info[..., 2]
        
        return keypoints, scores, det_result