提交RetinaFace推理示例

models/retinaface.py

+import torch
+import torch.nn as nn
+import torchvision.models.detection.backbone_utils as backbone_utils
+import torchvision.models._utils as _utils
+import torch.nn.functional as F
+from collections import OrderedDict
+
+from models.net import MobileNetV1 as MobileNetV1
+from models.net import FPN as FPN
+from models.net import SSH as SSH
+
+
+
+class ClassHead(nn.Module):
+    def __init__(self,inchannels=512,num_anchors=3):
+        super(ClassHead,self).__init__()
+        self.num_anchors = num_anchors
+        self.conv1x1 = nn.Conv2d(inchannels,self.num_anchors*2,kernel_size=(1,1),stride=1,padding=0)
+
+    def forward(self,x):
+        out = self.conv1x1(x)
+        out = out.permute(0,2,3,1).contiguous()
+        
+        return out.view(out.shape[0], -1, 2)
+
+class BboxHead(nn.Module):
+    def __init__(self,inchannels=512,num_anchors=3):
+        super(BboxHead,self).__init__()
+        self.conv1x1 = nn.Conv2d(inchannels,num_anchors*4,kernel_size=(1,1),stride=1,padding=0)
+
+    def forward(self,x):
+        out = self.conv1x1(x)
+        out = out.permute(0,2,3,1).contiguous()
+
+        return out.view(out.shape[0], -1, 4)
+
+class LandmarkHead(nn.Module):
+    def __init__(self,inchannels=512,num_anchors=3):
+        super(LandmarkHead,self).__init__()
+        self.conv1x1 = nn.Conv2d(inchannels,num_anchors*10,kernel_size=(1,1),stride=1,padding=0)
+
+    def forward(self,x):
+        out = self.conv1x1(x)
+        out = out.permute(0,2,3,1).contiguous()
+
+        return out.view(out.shape[0], -1, 10)
+
+class RetinaFace(nn.Module):
+    def __init__(self, cfg = None, phase = 'train'):
+        """
+        :param cfg:  Network related settings.
+        :param phase: train or test.
+        """
+        super(RetinaFace,self).__init__()
+        self.phase = phase
+        backbone = None
+        if cfg['name'] == 'mobilenet0.25':
+            backbone = MobileNetV1()
+            if cfg['pretrain']:
+                checkpoint = torch.load("./weights/mobilenetV1X0.25_pretrain.tar", map_location=torch.device('cpu'))
+                from collections import OrderedDict
+                new_state_dict = OrderedDict()
+                for k, v in checkpoint['state_dict'].items():
+                    name = k[7:]  # remove module.
+                    new_state_dict[name] = v
+                # load params
+                backbone.load_state_dict(new_state_dict)
+        elif cfg['name'] == 'Resnet50':
+            import torchvision.models as models
+            backbone = models.resnet50(pretrained=cfg['pretrain'])
+
+        self.body = _utils.IntermediateLayerGetter(backbone, cfg['return_layers'])
+        in_channels_stage2 = cfg['in_channel']
+        in_channels_list = [
+            in_channels_stage2 * 2,
+            in_channels_stage2 * 4,
+            in_channels_stage2 * 8,
+        ]
+        out_channels = cfg['out_channel']
+        self.fpn = FPN(in_channels_list,out_channels)
+        self.ssh1 = SSH(out_channels, out_channels)
+        self.ssh2 = SSH(out_channels, out_channels)
+        self.ssh3 = SSH(out_channels, out_channels)
+
+        self.ClassHead = self._make_class_head(fpn_num=3, inchannels=cfg['out_channel'])
+        self.BboxHead = self._make_bbox_head(fpn_num=3, inchannels=cfg['out_channel'])
+        self.LandmarkHead = self._make_landmark_head(fpn_num=3, inchannels=cfg['out_channel'])
+
+    def _make_class_head(self,fpn_num=3,inchannels=64,anchor_num=2):
+        classhead = nn.ModuleList()
+        for i in range(fpn_num):
+            classhead.append(ClassHead(inchannels,anchor_num))
+        return classhead
+    
+    def _make_bbox_head(self,fpn_num=3,inchannels=64,anchor_num=2):
+        bboxhead = nn.ModuleList()
+        for i in range(fpn_num):
+            bboxhead.append(BboxHead(inchannels,anchor_num))
+        return bboxhead
+
+    def _make_landmark_head(self,fpn_num=3,inchannels=64,anchor_num=2):
+        landmarkhead = nn.ModuleList()
+        for i in range(fpn_num):
+            landmarkhead.append(LandmarkHead(inchannels,anchor_num))
+        return landmarkhead
+
+    def forward(self,inputs):
+        out = self.body(inputs)
+
+        # FPN
+        fpn = self.fpn(out)
+
+        # SSH
+        feature1 = self.ssh1(fpn[0])
+        feature2 = self.ssh2(fpn[1])
+        feature3 = self.ssh3(fpn[2])
+        features = [feature1, feature2, feature3]
+
+        bbox_regressions = torch.cat([self.BboxHead[i](feature) for i, feature in enumerate(features)], dim=1)
+        classifications = torch.cat([self.ClassHead[i](feature) for i, feature in enumerate(features)],dim=1)
+        ldm_regressions = torch.cat([self.LandmarkHead[i](feature) for i, feature in enumerate(features)], dim=1)
+
+        if self.phase == 'train':
+            output = (bbox_regressions, classifications, ldm_regressions)
+        else:
+            output = (bbox_regressions, F.softmax(classifications, dim=-1), ldm_regressions)
+        return output
\ No newline at end of file

requirements.txt

+opencv-python
+numpy

test_fddb.py

+from __future__ import print_function
+import os
+import argparse
+import torch
+import torch.backends.cudnn as cudnn
+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
+from utils.timer import Timer
+
+parser = argparse.ArgumentParser(description='Retinaface')
+
+parser.add_argument('-m', '--trained_model', default='./weights/mobilenet0.25_Final.pth',
+                    type=str, help='Trained state_dict file path to open')
+parser.add_argument('--network', default='mobile0.25', help='Backbone network mobile0.25 or resnet50')
+parser.add_argument('--save_folder', default='eval/', type=str, help='Dir to save results')
+parser.add_argument('--cpu', action="store_true", default=False, help='Use cpu inference')
+parser.add_argument('--dataset', default='FDDB', type=str, choices=['FDDB'], help='dataset')
+parser.add_argument('--confidence_threshold', default=0.02, type=float, help='confidence_threshold')
+parser.add_argument('--top_k', default=5000, type=int, help='top_k')
+parser.add_argument('--nms_threshold', default=0.4, type=float, help='nms_threshold')
+parser.add_argument('--keep_top_k', default=750, type=int, help='keep_top_k')
+parser.add_argument('-s', '--save_image', action="store_true", default=False, help='show detection results')
+parser.add_argument('--vis_thres', default=0.5, type=float, help='visualization_threshold')
+args = parser.parse_args()
+
+
+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
+
+
+if __name__ == '__main__':
+    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!')
+    print(net)
+    cudnn.benchmark = True
+    device = torch.device("cpu" if args.cpu else "cuda")
+    net = net.to(device)
+
+
+    # save file
+    if not os.path.exists(args.save_folder):
+        os.makedirs(args.save_folder)
+    fw = open(os.path.join(args.save_folder, args.dataset + '_dets.txt'), 'w')
+
+    # testing dataset
+    testset_folder = os.path.join('data', args.dataset, 'images/')
+    testset_list = os.path.join('data', args.dataset, 'img_list.txt')
+    with open(testset_list, 'r') as fr:
+        test_dataset = fr.read().split()
+    num_images = len(test_dataset)
+
+    # testing scale
+    resize = 1
+
+    _t = {'forward_pass': Timer(), 'misc': Timer()}
+
+    # testing begin
+    for i, img_name in enumerate(test_dataset):
+        image_path = testset_folder + img_name + '.jpg'
+        img_raw = cv2.imread(image_path, cv2.IMREAD_COLOR)
+
+        img = np.float32(img_raw)
+        if resize != 1:
+            img = cv2.resize(img, None, None, fx=resize, fy=resize, interpolation=cv2.INTER_LINEAR)
+        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)
+
+        _t['forward_pass'].tic()
+        loc, conf, landms = net(img)  # forward pass
+        _t['forward_pass'].toc()
+        _t['misc'].tic()
+        priorbox = PriorBox(cfg, image_size=(im_height, im_width))
+        priors = priorbox.forward()
+        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]
+        order = scores.argsort()[::-1]
+        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)
+
+        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)
+        _t['misc'].toc()
+
+        # save dets
+        if args.dataset == "FDDB":
+            fw.write('{:s}\n'.format(img_name))
+            fw.write('{:.1f}\n'.format(dets.shape[0]))
+            for k in range(dets.shape[0]):
+                xmin = dets[k, 0]
+                ymin = dets[k, 1]
+                xmax = dets[k, 2]
+                ymax = dets[k, 3]
+                score = dets[k, 4]
+                w = xmax - xmin + 1
+                h = ymax - ymin + 1
+                # fw.write('{:.3f} {:.3f} {:.3f} {:.3f} {:.10f}\n'.format(xmin, ymin, w, h, score))
+                fw.write('{:d} {:d} {:d} {:d} {:.10f}\n'.format(int(xmin), int(ymin), int(w), int(h), score))
+        print('im_detect: {:d}/{:d} forward_pass_time: {:.4f}s misc: {:.4f}s'.format(i + 1, num_images, _t['forward_pass'].average_time, _t['misc'].average_time))
+
+        # show image
+        if args.save_image:
+            for b in dets:
+                if b[4] < args.vis_thres:
+                    continue
+                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), 2)
+                cx = b[0]
+                cy = b[1] + 12
+                cv2.putText(img_raw, text, (cx, cy),
+                            cv2.FONT_HERSHEY_DUPLEX, 0.5, (255, 255, 255))
+
+                # 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)
+            # save image
+            if not os.path.exists("./results/"):
+                os.makedirs("./results/")
+            name = "./results/" + str(i) + ".jpg"
+            cv2.imwrite(name, img_raw)
+
+    fw.close()

test_widerface.py

+from __future__ import print_function
+import os
+import argparse
+import torch
+import torch.backends.cudnn as cudnn
+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
+from utils.timer import Timer
+
+
+parser = argparse.ArgumentParser(description='Retinaface')
+parser.add_argument('-m', '--trained_model', default='./weights/Resnet50_Final.pth',
+                    type=str, help='Trained state_dict file path to open')
+parser.add_argument('--network', default='resnet50', help='Backbone network mobile0.25 or resnet50')
+parser.add_argument('--origin_size', default=True, type=str, help='Whether use origin image size to evaluate')
+parser.add_argument('--save_folder', default='./widerface_evaluate/widerface_txt/', type=str, help='Dir to save txt results')
+parser.add_argument('--cpu', action="store_true", default=False, help='Use cpu inference')
+parser.add_argument('--dataset_folder', default='./data/widerface/val/images/', type=str, help='dataset path')
+parser.add_argument('--confidence_threshold', default=0.02, type=float, help='confidence_threshold')
+parser.add_argument('--top_k', default=5000, type=int, help='top_k')
+parser.add_argument('--nms_threshold', default=0.4, type=float, help='nms_threshold')
+parser.add_argument('--keep_top_k', default=750, type=int, help='keep_top_k')
+parser.add_argument('-s', '--save_image', action="store_true", default=False, help='show detection results')
+parser.add_argument('--vis_thres', default=0.5, type=float, help='visualization_threshold')
+args = parser.parse_args()
+
+
+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
+
+
+if __name__ == '__main__':
+    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!')
+    print(net)
+    cudnn.benchmark = True
+    device = torch.device("cpu" if args.cpu else "cuda")
+    net = net.to(device)
+
+    # testing dataset
+    testset_folder = args.dataset_folder
+    testset_list = args.dataset_folder[:-7] + "wider_val.txt"
+
+    with open(testset_list, 'r') as fr:
+        test_dataset = fr.read().split()
+    num_images = len(test_dataset)
+
+    _t = {'forward_pass': Timer(), 'misc': Timer()}
+
+    # testing begin
+    for i, img_name in enumerate(test_dataset):
+        image_path = testset_folder + img_name
+        img_raw = cv2.imread(image_path, cv2.IMREAD_COLOR)
+        img = np.float32(img_raw)
+
+        # testing scale
+        target_size = 1600
+        max_size = 2150
+        im_shape = img.shape
+        im_size_min = np.min(im_shape[0:2])
+        im_size_max = np.max(im_shape[0:2])
+        resize = float(target_size) / float(im_size_min)
+        # prevent bigger axis from being more than max_size:
+        if np.round(resize * im_size_max) > max_size:
+            resize = float(max_size) / float(im_size_max)
+        if args.origin_size:
+            resize = 1
+
+        if resize != 1:
+            img = cv2.resize(img, None, None, fx=resize, fy=resize, interpolation=cv2.INTER_LINEAR)
+        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)
+
+        _t['forward_pass'].tic()
+        loc, conf, landms = net(img)  # forward pass
+        _t['forward_pass'].toc()
+        _t['misc'].tic()
+        priorbox = PriorBox(cfg, image_size=(im_height, im_width))
+        priors = priorbox.forward()
+        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]
+        # 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)
+        _t['misc'].toc()
+
+        # --------------------------------------------------------------------
+        save_name = args.save_folder + img_name[:-4] + ".txt"
+        dirname = os.path.dirname(save_name)
+        if not os.path.isdir(dirname):
+            os.makedirs(dirname)
+        with open(save_name, "w") as fd:
+            bboxs = dets
+            file_name = os.path.basename(save_name)[:-4] + "\n"
+            bboxs_num = str(len(bboxs)) + "\n"
+            fd.write(file_name)
+            fd.write(bboxs_num)
+            for box in bboxs:
+                x = int(box[0])
+                y = int(box[1])
+                w = int(box[2]) - int(box[0])
+                h = int(box[3]) - int(box[1])
+                confidence = str(box[4])
+                line = str(x) + " " + str(y) + " " + str(w) + " " + str(h) + " " + confidence + " \n"
+                fd.write(line)
+
+        print('im_detect: {:d}/{:d} forward_pass_time: {:.4f}s misc: {:.4f}s'.format(i + 1, num_images, _t['forward_pass'].average_time, _t['misc'].average_time))
+
+        # save image
+        if args.save_image:
+            for b in dets:
+                if b[4] < args.vis_thres:
+                    continue
+                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), 2)
+                cx = b[0]
+                cy = b[1] + 12
+                cv2.putText(img_raw, text, (cx, cy),
+                            cv2.FONT_HERSHEY_DUPLEX, 0.5, (255, 255, 255))
+
+                # 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)
+            # save image
+            if not os.path.exists("./results/"):
+                os.makedirs("./results/")
+            name = "./results/" + str(i) + ".jpg"
+            cv2.imwrite(name, img_raw)
+

train.py

+from __future__ import print_function
+import os
+import torch
+import torch.optim as optim
+import torch.backends.cudnn as cudnn
+import argparse
+import torch.utils.data as data
+from data import WiderFaceDetection, detection_collate, preproc, cfg_mnet, cfg_re50
+from layers.modules import MultiBoxLoss
+from layers.functions.prior_box import PriorBox
+import time
+import datetime
+import math
+from models.retinaface import RetinaFace
+
+parser = argparse.ArgumentParser(description='Retinaface Training')
+parser.add_argument('--training_dataset', default='./data/widerface/train/label.txt', help='Training dataset directory')
+parser.add_argument('--network', default='mobile0.25', help='Backbone network mobile0.25 or resnet50')
+parser.add_argument('--num_workers', default=4, type=int, help='Number of workers used in dataloading')
+parser.add_argument('--lr', '--learning-rate', default=1e-3, type=float, help='initial learning rate')
+parser.add_argument('--momentum', default=0.9, type=float, help='momentum')
+parser.add_argument('--resume_net', default=None, help='resume net for retraining')
+parser.add_argument('--resume_epoch', default=0, type=int, help='resume iter for retraining')
+parser.add_argument('--weight_decay', default=5e-4, type=float, help='Weight decay for SGD')
+parser.add_argument('--gamma', default=0.1, type=float, help='Gamma update for SGD')
+parser.add_argument('--save_folder', default='./weights/', help='Location to save checkpoint models')
+
+args = parser.parse_args()
+
+if not os.path.exists(args.save_folder):
+    os.mkdir(args.save_folder)
+cfg = None
+if args.network == "mobile0.25":
+    cfg = cfg_mnet
+elif args.network == "resnet50":
+    cfg = cfg_re50
+
+rgb_mean = (104, 117, 123) # bgr order
+num_classes = 2
+img_dim = cfg['image_size']
+num_gpu = cfg['ngpu']
+batch_size = cfg['batch_size']
+max_epoch = cfg['epoch']
+gpu_train = cfg['gpu_train']
+
+num_workers = args.num_workers
+momentum = args.momentum
+weight_decay = args.weight_decay
+initial_lr = args.lr
+gamma = args.gamma
+training_dataset = args.training_dataset
+save_folder = args.save_folder
+
+net = RetinaFace(cfg=cfg)
+print("Printing net...")
+print(net)
+
+if args.resume_net is not None:
+    print('Loading resume network...')
+    state_dict = torch.load(args.resume_net)
+    # create new OrderedDict that does not contain `module.`
+    from collections import OrderedDict
+    new_state_dict = OrderedDict()
+    for k, v in state_dict.items():
+        head = k[:7]
+        if head == 'module.':
+            name = k[7:] # remove `module.`
+        else:
+            name = k
+        new_state_dict[name] = v
+    net.load_state_dict(new_state_dict)
+
+if num_gpu > 1 and gpu_train:
+    net = torch.nn.DataParallel(net).cuda()
+else:
+    net = net.cuda()
+
+cudnn.benchmark = True
+
+
+optimizer = optim.SGD(net.parameters(), lr=initial_lr, momentum=momentum, weight_decay=weight_decay)
+criterion = MultiBoxLoss(num_classes, 0.35, True, 0, True, 7, 0.35, False)
+
+priorbox = PriorBox(cfg, image_size=(img_dim, img_dim))
+with torch.no_grad():
+    priors = priorbox.forward()
+    priors = priors.cuda()
+
+def train():
+    net.train()
+    epoch = 0 + args.resume_epoch
+    print('Loading Dataset...')
+
+    dataset = WiderFaceDetection( training_dataset,preproc(img_dim, rgb_mean))
+
+    epoch_size = math.ceil(len(dataset) / batch_size)
+    max_iter = max_epoch * epoch_size
+
+    stepvalues = (cfg['decay1'] * epoch_size, cfg['decay2'] * epoch_size)
+    step_index = 0
+
+    if args.resume_epoch > 0:
+        start_iter = args.resume_epoch * epoch_size
+    else:
+        start_iter = 0
+
+    for iteration in range(start_iter, max_iter):
+        if iteration % epoch_size == 0:
+            # create batch iterator
+            batch_iterator = iter(data.DataLoader(dataset, batch_size, shuffle=True, num_workers=num_workers, collate_fn=detection_collate))
+            if (epoch % 10 == 0 and epoch > 0) or (epoch % 5 == 0 and epoch > cfg['decay1']):
+                torch.save(net.state_dict(), save_folder + cfg['name']+ '_epoch_' + str(epoch) + '.pth')
+            epoch += 1
+
+        load_t0 = time.time()
+        if iteration in stepvalues:
+            step_index += 1
+        lr = adjust_learning_rate(optimizer, gamma, epoch, step_index, iteration, epoch_size)
+
+        # load train data
+        images, targets = next(batch_iterator)
+        images = images.cuda()
+        targets = [anno.cuda() for anno in targets]
+
+        # forward
+        out = net(images)
+
+        # backprop
+        optimizer.zero_grad()
+        loss_l, loss_c, loss_landm = criterion(out, priors, targets)
+        loss = cfg['loc_weight'] * loss_l + loss_c + loss_landm
+        loss.backward()
+        optimizer.step()
+        load_t1 = time.time()
+        batch_time = load_t1 - load_t0
+        eta = int(batch_time * (max_iter - iteration))
+        print('Epoch:{}/{} || Epochiter: {}/{} || Iter: {}/{} || Loc: {:.4f} Cla: {:.4f} Landm: {:.4f} || LR: {:.8f} || Batchtime: {:.4f} s || ETA: {}'
+              .format(epoch, max_epoch, (iteration % epoch_size) + 1,
+              epoch_size, iteration + 1, max_iter, loss_l.item(), loss_c.item(), loss_landm.item(), lr, batch_time, str(datetime.timedelta(seconds=eta))))
+
+    torch.save(net.state_dict(), save_folder + cfg['name'] + '_Final.pth')
+    # torch.save(net.state_dict(), save_folder + 'Final_Retinaface.pth')
+
+
+def adjust_learning_rate(optimizer, gamma, epoch, step_index, iteration, epoch_size):
+    """Sets the learning rate
+    # Adapted from PyTorch Imagenet example:
+    # https://github.com/pytorch/examples/blob/master/imagenet/main.py
+    """
+    warmup_epoch = -1
+    if epoch <= warmup_epoch:
+        lr = 1e-6 + (initial_lr-1e-6) * iteration / (epoch_size * warmup_epoch)
+    else:
+        lr = initial_lr * (gamma ** (step_index))
+    for param_group in optimizer.param_groups:
+        param_group['lr'] = lr
+    return lr
+
+if __name__ == '__main__':
+    train()

utils/box_utils.py

+import torch
+import numpy as np
+
+
+def point_form(boxes):
+    """ Convert prior_boxes to (xmin, ymin, xmax, ymax)
+    representation for comparison to point form ground truth data.
+    Args:
+        boxes: (tensor) center-size default boxes from priorbox layers.
+    Return:
+        boxes: (tensor) Converted xmin, ymin, xmax, ymax form of boxes.
+    """
+    return torch.cat((boxes[:, :2] - boxes[:, 2:]/2,     # xmin, ymin
+                     boxes[:, :2] + boxes[:, 2:]/2), 1)  # xmax, ymax
+
+
+def center_size(boxes):
+    """ Convert prior_boxes to (cx, cy, w, h)
+    representation for comparison to center-size form ground truth data.
+    Args:
+        boxes: (tensor) point_form boxes
+    Return:
+        boxes: (tensor) Converted xmin, ymin, xmax, ymax form of boxes.
+    """
+    return torch.cat((boxes[:, 2:] + boxes[:, :2])/2,  # cx, cy
+                     boxes[:, 2:] - boxes[:, :2], 1)  # w, h
+
+
+def intersect(box_a, box_b):
+    """ We resize both tensors to [A,B,2] without new malloc:
+    [A,2] -> [A,1,2] -> [A,B,2]
+    [B,2] -> [1,B,2] -> [A,B,2]
+    Then we compute the area of intersect between box_a and box_b.
+    Args:
+      box_a: (tensor) bounding boxes, Shape: [A,4].
+      box_b: (tensor) bounding boxes, Shape: [B,4].
+    Return:
+      (tensor) intersection area, Shape: [A,B].
+    """
+    A = box_a.size(0)
+    B = box_b.size(0)
+    max_xy = torch.min(box_a[:, 2:].unsqueeze(1).expand(A, B, 2),
+                       box_b[:, 2:].unsqueeze(0).expand(A, B, 2))
+    min_xy = torch.max(box_a[:, :2].unsqueeze(1).expand(A, B, 2),
+                       box_b[:, :2].unsqueeze(0).expand(A, B, 2))
+    inter = torch.clamp((max_xy - min_xy), min=0)
+    return inter[:, :, 0] * inter[:, :, 1]
+
+
+def jaccard(box_a, box_b):
+    """Compute the jaccard overlap of two sets of boxes.  The jaccard overlap
+    is simply the intersection over union of two boxes.  Here we operate on
+    ground truth boxes and default boxes.
+    E.g.:
+        A ∩ B / A ∪ B = A ∩ B / (area(A) + area(B) - A ∩ B)
+    Args:
+        box_a: (tensor) Ground truth bounding boxes, Shape: [num_objects,4]
+        box_b: (tensor) Prior boxes from priorbox layers, Shape: [num_priors,4]
+    Return:
+        jaccard overlap: (tensor) Shape: [box_a.size(0), box_b.size(0)]
+    """
+    inter = intersect(box_a, box_b)
+    area_a = ((box_a[:, 2]-box_a[:, 0]) *
+              (box_a[:, 3]-box_a[:, 1])).unsqueeze(1).expand_as(inter)  # [A,B]
+    area_b = ((box_b[:, 2]-box_b[:, 0]) *
+              (box_b[:, 3]-box_b[:, 1])).unsqueeze(0).expand_as(inter)  # [A,B]
+    union = area_a + area_b - inter
+    return inter / union  # [A,B]
+
+
+def matrix_iou(a, b):
+    """
+    return iou of a and b, numpy version for data augenmentation
+    """
+    lt = np.maximum(a[:, np.newaxis, :2], b[:, :2])
+    rb = np.minimum(a[:, np.newaxis, 2:], b[:, 2:])
+
+    area_i = np.prod(rb - lt, axis=2) * (lt < rb).all(axis=2)
+    area_a = np.prod(a[:, 2:] - a[:, :2], axis=1)
+    area_b = np.prod(b[:, 2:] - b[:, :2], axis=1)
+    return area_i / (area_a[:, np.newaxis] + area_b - area_i)
+
+
+def matrix_iof(a, b):
+    """
+    return iof of a and b, numpy version for data augenmentation
+    """
+    lt = np.maximum(a[:, np.newaxis, :2], b[:, :2])
+    rb = np.minimum(a[:, np.newaxis, 2:], b[:, 2:])
+
+    area_i = np.prod(rb - lt, axis=2) * (lt < rb).all(axis=2)
+    area_a = np.prod(a[:, 2:] - a[:, :2], axis=1)
+    return area_i / np.maximum(area_a[:, np.newaxis], 1)
+
+
+def match(threshold, truths, priors, variances, labels, landms, loc_t, conf_t, landm_t, idx):
+    """Match each prior box with the ground truth box of the highest jaccard
+    overlap, encode the bounding boxes, then return the matched indices
+    corresponding to both confidence and location preds.
+    Args:
+        threshold: (float) The overlap threshold used when mathing boxes.
+        truths: (tensor) Ground truth boxes, Shape: [num_obj, 4].
+        priors: (tensor) Prior boxes from priorbox layers, Shape: [n_priors,4].
+        variances: (tensor) Variances corresponding to each prior coord,
+            Shape: [num_priors, 4].
+        labels: (tensor) All the class labels for the image, Shape: [num_obj].
+        landms: (tensor) Ground truth landms, Shape [num_obj, 10].
+        loc_t: (tensor) Tensor to be filled w/ endcoded location targets.
+        conf_t: (tensor) Tensor to be filled w/ matched indices for conf preds.
+        landm_t: (tensor) Tensor to be filled w/ endcoded landm targets.
+        idx: (int) current batch index
+    Return:
+        The matched indices corresponding to 1)location 2)confidence 3)landm preds.
+    """
+    # jaccard index
+    overlaps = jaccard(
+        truths,
+        point_form(priors)
+    )
+    # (Bipartite Matching)
+    # [1,num_objects] best prior for each ground truth
+    best_prior_overlap, best_prior_idx = overlaps.max(1, keepdim=True)
+
+    # ignore hard gt
+    valid_gt_idx = best_prior_overlap[:, 0] >= 0.2
+    best_prior_idx_filter = best_prior_idx[valid_gt_idx, :]
+    if best_prior_idx_filter.shape[0] <= 0:
+        loc_t[idx] = 0
+        conf_t[idx] = 0
+        return
+
+    # [1,num_priors] best ground truth for each prior
+    best_truth_overlap, best_truth_idx = overlaps.max(0, keepdim=True)
+    best_truth_idx.squeeze_(0)
+    best_truth_overlap.squeeze_(0)
+    best_prior_idx.squeeze_(1)
+    best_prior_idx_filter.squeeze_(1)
+    best_prior_overlap.squeeze_(1)
+    best_truth_overlap.index_fill_(0, best_prior_idx_filter, 2)  # ensure best prior
+    # TODO refactor: index  best_prior_idx with long tensor
+    # ensure every gt matches with its prior of max overlap
+    for j in range(best_prior_idx.size(0)):     # 判别此anchor是预测哪一个boxes
+        best_truth_idx[best_prior_idx[j]] = j
+    matches = truths[best_truth_idx]            # Shape: [num_priors,4] 此处为每一个anchor对应的bbox取出来
+    conf = labels[best_truth_idx]               # Shape: [num_priors]      此处为每一个anchor对应的label取出来
+    conf[best_truth_overlap < threshold] = 0    # label as background   overlap<0.35的全部作为负样本
+    loc = encode(matches, priors, variances)
+
+    matches_landm = landms[best_truth_idx]
+    landm = encode_landm(matches_landm, priors, variances)
+    loc_t[idx] = loc    # [num_priors,4] encoded offsets to learn
+    conf_t[idx] = conf  # [num_priors] top class label for each prior
+    landm_t[idx] = landm
+
+
+def encode(matched, priors, variances):
+    """Encode the variances from the priorbox layers into the ground truth boxes
+    we have matched (based on jaccard overlap) with the prior boxes.
+    Args:
+        matched: (tensor) Coords of ground truth for each prior in point-form
+            Shape: [num_priors, 4].
+        priors: (tensor) Prior boxes in center-offset form
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        encoded boxes (tensor), Shape: [num_priors, 4]
+    """
+
+    # dist b/t match center and prior's center
+    g_cxcy = (matched[:, :2] + matched[:, 2:])/2 - priors[:, :2]
+    # encode variance
+    g_cxcy /= (variances[0] * priors[:, 2:])
+    # match wh / prior wh
+    g_wh = (matched[:, 2:] - matched[:, :2]) / priors[:, 2:]
+    g_wh = torch.log(g_wh) / variances[1]
+    # return target for smooth_l1_loss
+    return torch.cat([g_cxcy, g_wh], 1)  # [num_priors,4]
+
+def encode_landm(matched, priors, variances):
+    """Encode the variances from the priorbox layers into the ground truth boxes
+    we have matched (based on jaccard overlap) with the prior boxes.
+    Args:
+        matched: (tensor) Coords of ground truth for each prior in point-form
+            Shape: [num_priors, 10].
+        priors: (tensor) Prior boxes in center-offset form
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        encoded landm (tensor), Shape: [num_priors, 10]
+    """
+
+    # dist b/t match center and prior's center
+    matched = torch.reshape(matched, (matched.size(0), 5, 2))
+    priors_cx = priors[:, 0].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_cy = priors[:, 1].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_w = priors[:, 2].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors_h = priors[:, 3].unsqueeze(1).expand(matched.size(0), 5).unsqueeze(2)
+    priors = torch.cat([priors_cx, priors_cy, priors_w, priors_h], dim=2)
+    g_cxcy = matched[:, :, :2] - priors[:, :, :2]
+    # encode variance
+    g_cxcy /= (variances[0] * priors[:, :, 2:])
+    # g_cxcy /= priors[:, :, 2:]
+    g_cxcy = g_cxcy.reshape(g_cxcy.size(0), -1)
+    # return target for smooth_l1_loss
+    return g_cxcy
+
+
+# Adapted from https://github.com/Hakuyume/chainer-ssd
+def decode(loc, priors, variances):
+    """Decode locations from predictions using priors to undo
+    the encoding we did for offset regression at train time.
+    Args:
+        loc (tensor): location predictions for loc layers,
+            Shape: [num_priors,4]
+        priors (tensor): Prior boxes in center-offset form.
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        decoded bounding box predictions
+    """
+
+    boxes = torch.cat((
+        priors[:, :2] + loc[:, :2] * variances[0] * priors[:, 2:],
+        priors[:, 2:] * torch.exp(loc[:, 2:] * variances[1])), 1)
+    boxes[:, :2] -= boxes[:, 2:] / 2
+    boxes[:, 2:] += boxes[:, :2]
+    return boxes
+
+def decode_landm(pre, priors, variances):
+    """Decode landm from predictions using priors to undo
+    the encoding we did for offset regression at train time.
+    Args:
+        pre (tensor): landm predictions for loc layers,
+            Shape: [num_priors,10]
+        priors (tensor): Prior boxes in center-offset form.
+            Shape: [num_priors,4].
+        variances: (list[float]) Variances of priorboxes
+    Return:
+        decoded landm predictions
+    """
+    landms = torch.cat((priors[:, :2] + pre[:, :2] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 2:4] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 4:6] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 6:8] * variances[0] * priors[:, 2:],
+                        priors[:, :2] + pre[:, 8:10] * variances[0] * priors[:, 2:],
+                        ), dim=1)
+    return landms
+
+
+def log_sum_exp(x):
+    """Utility function for computing log_sum_exp while determining
+    This will be used to determine unaveraged confidence loss across
+    all examples in a batch.
+    Args:
+        x (Variable(tensor)): conf_preds from conf layers
+    """
+    x_max = x.data.max()
+    return torch.log(torch.sum(torch.exp(x-x_max), 1, keepdim=True)) + x_max
+
+
+# Original author: Francisco Massa:
+# https://github.com/fmassa/object-detection.torch
+# Ported to PyTorch by Max deGroot (02/01/2017)
+def nms(boxes, scores, overlap=0.5, top_k=200):
+    """Apply non-maximum suppression at test time to avoid detecting too many
+    overlapping bounding boxes for a given object.
+    Args:
+        boxes: (tensor) The location preds for the img, Shape: [num_priors,4].
+        scores: (tensor) The class predscores for the img, Shape:[num_priors].
+        overlap: (float) The overlap thresh for suppressing unnecessary boxes.
+        top_k: (int) The Maximum number of box preds to consider.
+    Return:
+        The indices of the kept boxes with respect to num_priors.
+    """
+
+    keep = torch.Tensor(scores.size(0)).fill_(0).long()
+    if boxes.numel() == 0:
+        return keep
+    x1 = boxes[:, 0]
+    y1 = boxes[:, 1]
+    x2 = boxes[:, 2]
+    y2 = boxes[:, 3]
+    area = torch.mul(x2 - x1, y2 - y1)
+    v, idx = scores.sort(0)  # sort in ascending order
+    # I = I[v >= 0.01]
+    idx = idx[-top_k:]  # indices of the top-k largest vals
+    xx1 = boxes.new()
+    yy1 = boxes.new()
+    xx2 = boxes.new()
+    yy2 = boxes.new()
+    w = boxes.new()
+    h = boxes.new()
+
+    # keep = torch.Tensor()
+    count = 0
+    while idx.numel() > 0:
+        i = idx[-1]  # index of current largest val
+        # keep.append(i)
+        keep[count] = i
+        count += 1
+        if idx.size(0) == 1:
+            break
+        idx = idx[:-1]  # remove kept element from view
+        # load bboxes of next highest vals
+        torch.index_select(x1, 0, idx, out=xx1)
+        torch.index_select(y1, 0, idx, out=yy1)
+        torch.index_select(x2, 0, idx, out=xx2)
+        torch.index_select(y2, 0, idx, out=yy2)
+        # store element-wise max with next highest score
+        xx1 = torch.clamp(xx1, min=x1[i])
+        yy1 = torch.clamp(yy1, min=y1[i])
+        xx2 = torch.clamp(xx2, max=x2[i])
+        yy2 = torch.clamp(yy2, max=y2[i])
+        w.resize_as_(xx2)
+        h.resize_as_(yy2)
+        w = xx2 - xx1
+        h = yy2 - yy1
+        # check sizes of xx1 and xx2.. after each iteration
+        w = torch.clamp(w, min=0.0)
+        h = torch.clamp(h, min=0.0)
+        inter = w*h
+        # IoU = i / (area(a) + area(b) - i)
+        rem_areas = torch.index_select(area, 0, idx)  # load remaining areas)
+        union = (rem_areas - inter) + area[i]
+        IoU = inter/union  # store result in iou
+        # keep only elements with an IoU <= overlap
+        idx = idx[IoU.le(overlap)]
+    return keep, count
+
+

utils/nms/py_cpu_nms.py

+# --------------------------------------------------------
+# Fast R-CNN
+# Copyright (c) 2015 Microsoft
+# Licensed under The MIT License [see LICENSE for details]
+# Written by Ross Girshick
+# --------------------------------------------------------
+
+import numpy as np
+
+def py_cpu_nms(dets, thresh):
+    """Pure Python NMS baseline."""
+    x1 = dets[:, 0]
+    y1 = dets[:, 1]
+    x2 = dets[:, 2]
+    y2 = dets[:, 3]
+    scores = dets[:, 4]
+
+    areas = (x2 - x1 + 1) * (y2 - y1 + 1)
+    order = scores.argsort()[::-1]
+
+    keep = []
+    while order.size > 0:
+        i = order[0]
+        keep.append(i)
+        xx1 = np.maximum(x1[i], x1[order[1:]])
+        yy1 = np.maximum(y1[i], y1[order[1:]])
+        xx2 = np.minimum(x2[i], x2[order[1:]])
+        yy2 = np.minimum(y2[i], y2[order[1:]])
+
+        w = np.maximum(0.0, xx2 - xx1 + 1)
+        h = np.maximum(0.0, yy2 - yy1 + 1)
+        inter = w * h
+        ovr = inter / (areas[i] + areas[order[1:]] - inter)
+
+        inds = np.where(ovr <= thresh)[0]
+        order = order[inds + 1]
+
+    return keep

utils/timer.py

+# --------------------------------------------------------
+# Fast R-CNN
+# Copyright (c) 2015 Microsoft
+# Licensed under The MIT License [see LICENSE for details]
+# Written by Ross Girshick
+# --------------------------------------------------------
+
+import time
+
+
+class Timer(object):
+    """A simple timer."""
+    def __init__(self):
+        self.total_time = 0.
+        self.calls = 0
+        self.start_time = 0.
+        self.diff = 0.
+        self.average_time = 0.
+
+    def tic(self):
+        # using time.time instead of time.clock because time time.clock
+        # does not normalize for multithreading
+        self.start_time = time.time()
+
+    def toc(self, average=True):
+        self.diff = time.time() - self.start_time
+        self.total_time += self.diff
+        self.calls += 1
+        self.average_time = self.total_time / self.calls
+        if average:
+            return self.average_time
+        else:
+            return self.diff
+
+    def clear(self):
+        self.total_time = 0.
+        self.calls = 0
+        self.start_time = 0.
+        self.diff = 0.
+        self.average_time = 0.

widerface_evaluate/README.md

+# WiderFace-Evaluation
+Python Evaluation Code for [Wider Face Dataset](http://mmlab.ie.cuhk.edu.hk/projects/WIDERFace/)
+
+
+## Usage
+
+
+##### before evaluating ....
+
+````
+python3 setup.py build_ext --inplace
+````
+
+##### evaluating
+
+**GroungTruth:** `wider_face_val.mat`, `wider_easy_val.mat`, `wider_medium_val.mat`,`wider_hard_val.mat`
+
+````
+python3 evaluation.py -p <your prediction dir> -g <groud truth dir>
+````
+
+## Bugs & Problems
+please issue
+
+## Acknowledgements
+
+some code borrowed from Sergey Karayev