face_detector.py

import os
import torch
import numpy as np
from data import cfg_mnet, cfg_re50
from layers.functions.prior_box import PriorBox
from utils.nms.py_cpu_nms import py_cpu_nms
import cv2
from models.retinaface import RetinaFace
from utils.box_utils import decode, decode_landm

class CONFIG:
    network = "resnet50"
    cpu = True      # Use cpu inference
    top_k = 5000
    nms_threshold = 0.4
    keep_top_k  = 750
    save_image  = True
    vis_thres = 0.6
    trained_model = "./weights/Resnet50_Final.pth"
    confidence_threshold = 0.02

def check_keys(model, pretrained_state_dict):
    ckpt_keys = set(pretrained_state_dict.keys())
    model_keys = set(model.state_dict().keys())
    used_pretrained_keys = model_keys & ckpt_keys
    unused_pretrained_keys = ckpt_keys - model_keys
    missing_keys = model_keys - ckpt_keys
    print('Missing keys:{}'.format(len(missing_keys)))
    print('Unused checkpoint keys:{}'.format(len(unused_pretrained_keys)))
    print('Used keys:{}'.format(len(used_pretrained_keys)))
    assert len(used_pretrained_keys) > 0, 'load NONE from pretrained checkpoint'
    return True

def remove_prefix(state_dict, prefix):
    ''' Old style model is stored with all names of parameters sharing common prefix 'module.' '''
    print('remove prefix \'{}\''.format(prefix))
    f = lambda x: x.split(prefix, 1)[-1] if x.startswith(prefix) else x
    return {f(key): value for key, value in state_dict.items()}

def load_model(model, pretrained_path, load_to_cpu):
    print('Loading pretrained model from {}'.format(pretrained_path))
    if load_to_cpu:
        pretrained_dict = torch.load(pretrained_path, map_location=lambda storage, loc: storage)
    else:
        device = torch.cuda.current_device()
        pretrained_dict = torch.load(pretrained_path, map_location=lambda storage, loc: storage.cuda(device))
    if "state_dict" in pretrained_dict.keys():
        pretrained_dict = remove_prefix(pretrained_dict['state_dict'], 'module.')
    else:
        pretrained_dict = remove_prefix(pretrained_dict, 'module.')
    check_keys(model, pretrained_dict)
    model.load_state_dict(pretrained_dict, strict=False)
    return model

def show(img):
    cv2.imshow("res",img)
    cv2.waitKey(1)

def drawLandMark(img_raw,b):
    # landms
    cv2.circle(img_raw, (b[5], b[6]), 1, (0, 0, 255), 4)
    cv2.circle(img_raw, (b[7], b[8]), 1, (0, 255, 255), 4)
    cv2.circle(img_raw, (b[9], b[10]), 1, (255, 0, 255), 4)
    cv2.circle(img_raw, (b[11], b[12]), 1, (0, 255, 0), 4)
    cv2.circle(img_raw, (b[13], b[14]), 1, (255, 0, 0), 4)
    return img_raw

def loadNet(args):
    torch.set_grad_enabled(False)
    cfg = None
    if args.network == "mobile0.25":
        cfg = cfg_mnet
    elif args.network == "resnet50":
        cfg = cfg_re50
    # net and model
    net = RetinaFace(cfg=cfg, phase = 'test')
    net = load_model(net, args.trained_model, args.cpu)
    net.eval()
    print('Finished loading model!')
    device = torch.device("cpu" if args.cpu else "cuda")
    net = net.to(device)
    return net,device,cfg

def preProcess(img_raw,device):
    img = np.float32(img_raw)

    im_height, im_width, _ = img.shape
    scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
    img -= (104, 117, 123)
    img = img.transpose(2, 0, 1)
    img = torch.from_numpy(img).unsqueeze(0)
    img = img.to(device)
    scale = scale.to(device)

    return  img,scale,im_height, im_width

def inference(net,img,im_height, im_width,cfg):
    loc, conf, landms = net(img)  # forward pass

    priorbox = PriorBox(cfg, image_size=(im_height, im_width))
    priors = priorbox.forward()
    return conf,landms,priors,loc

def postProcess(args,scale,conf,landms,priors,cfg,img,device,loc):
    resize = 1
    priors = priors.to(device)
    prior_data = priors.data
    boxes = decode(loc.data.squeeze(0), prior_data, cfg['variance'])

    boxes = boxes * scale / resize
    boxes = boxes.cpu().numpy()
    scores = conf.squeeze(0).data.cpu().numpy()[:, 1]
    landms = decode_landm(landms.data.squeeze(0), prior_data, cfg['variance'])
    scale1 = torch.Tensor([img.shape[3], img.shape[2], img.shape[3], img.shape[2],
                           img.shape[3], img.shape[2], img.shape[3], img.shape[2],
                           img.shape[3], img.shape[2]])
    scale1 = scale1.to(device)
    landms = landms * scale1 / resize
    landms = landms.cpu().numpy()

    # ignore low scores
    inds = np.where(scores > args.confidence_threshold)[0]
    boxes = boxes[inds]
    landms = landms[inds]
    scores = scores[inds]

    # keep top-K before NMS
    order = scores.argsort()[::-1][:args.top_k]
    boxes = boxes[order]
    landms = landms[order]
    scores = scores[order]

    # do NMS
    dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
    keep = py_cpu_nms(dets, args.nms_threshold)
    # keep = nms(dets, args.nms_threshold,force_cpu=args.cpu)
    dets = dets[keep, :]
    landms = landms[keep]

    # keep top-K faster NMS
    dets = dets[:args.keep_top_k, :]
    landms = landms[:args.keep_top_k, :]

    dets = np.concatenate((dets, landms), axis=1)
    return dets

def fixResult(args,dets,img_raw,file,im_height, im_width):
    num = 0
    boxes = []
    if args.save_image:
        for b in dets:
            if b[4] < args.vis_thres:
                continue
            num+=1
            text = "{:.4f}".format(b[4])
            b = list(map(int, b))
            cv2.rectangle(img_raw, (b[0], b[1]), (b[2], b[3]), (0, 0, 255), 3)
            cx = b[0]
            cy = b[1] + 12
            cv2.putText(img_raw, text, (cx, cy),cv2.FONT_HERSHEY_DUPLEX, 0.7, (255, 255, 255))
            # print("{} @ ({} {} {} {})".format(text,b[0], b[1],b[2], b[3]) )
            boxes.append([b[0], b[1],b[2], b[3]] )

            # drawLandMark(img_raw,b)
        print("{}\t{}".format(file,num))
        # save image
        cv2.putText(img_raw, "total: "+str(num), (10,50),cv2.FONT_HERSHEY_DUPLEX, 1*(im_height* im_width)/(640*480)*0.5, (255, 0, 0),2)
        save_path = os.path.join("result",file)
        # show(img_raw)
        cv2.imwrite(save_path, img_raw)
    return boxes