diff --git a/.gitignore b/.gitignore
index 68bc17f..9f0d1b5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,6 @@
+outputs/
+**/Resnet50_Final.pth
+
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
diff --git a/Pytorch_Retinaface/data/__init__.py b/Pytorch_Retinaface/data/__init__.py
new file mode 100644
index 0000000..27c9ec6
--- /dev/null
+++ b/Pytorch_Retinaface/data/__init__.py
@@ -0,0 +1 @@
+from .config import *
diff --git a/Pytorch_Retinaface/data/config.py b/Pytorch_Retinaface/data/config.py
new file mode 100644
index 0000000..591f349
--- /dev/null
+++ b/Pytorch_Retinaface/data/config.py
@@ -0,0 +1,42 @@
+# config.py
+
+cfg_mnet = {
+    'name': 'mobilenet0.25',
+    'min_sizes': [[16, 32], [64, 128], [256, 512]],
+    'steps': [8, 16, 32],
+    'variance': [0.1, 0.2],
+    'clip': False,
+    'loc_weight': 2.0,
+    'gpu_train': True,
+    'batch_size': 32,
+    'ngpu': 1,
+    'epoch': 250,
+    'decay1': 190,
+    'decay2': 220,
+    'image_size': 640,
+    'pretrain': True,
+    'return_layers': {'stage1': 1, 'stage2': 2, 'stage3': 3},
+    'in_channel': 32,
+    'out_channel': 64
+}
+
+cfg_re50 = {
+    'name': 'Resnet50',
+    'min_sizes': [[16, 32], [64, 128], [256, 512]],
+    'steps': [8, 16, 32],
+    'variance': [0.1, 0.2],
+    'clip': False,
+    'loc_weight': 2.0,
+    'gpu_train': True,
+    'batch_size': 24,
+    'ngpu': 4,
+    'epoch': 100,
+    'decay1': 70,
+    'decay2': 90,
+    'image_size': 840,
+    'pretrain': True,
+    'return_layers': {'layer2': 1, 'layer3': 2, 'layer4': 3},
+    'in_channel': 256,
+    'out_channel': 256
+}
+
diff --git a/Pytorch_Retinaface/images/test.jpg b/Pytorch_Retinaface/images/test.jpg
new file mode 100644
index 0000000..4559d9f
Binary files /dev/null and b/Pytorch_Retinaface/images/test.jpg differ
diff --git a/Pytorch_Retinaface/images/test.webp b/Pytorch_Retinaface/images/test.webp
new file mode 100644
index 0000000..8005de7
Binary files /dev/null and b/Pytorch_Retinaface/images/test.webp differ
diff --git a/Pytorch_Retinaface/layers/__init__.py b/Pytorch_Retinaface/layers/__init__.py
new file mode 100644
index 0000000..c8f7548
--- /dev/null
+++ b/Pytorch_Retinaface/layers/__init__.py
@@ -0,0 +1 @@
+from .functions import *
diff --git a/Pytorch_Retinaface/layers/functions/prior_box.py b/Pytorch_Retinaface/layers/functions/prior_box.py
new file mode 100644
index 0000000..80c7f85
--- /dev/null
+++ b/Pytorch_Retinaface/layers/functions/prior_box.py
@@ -0,0 +1,34 @@
+import torch
+from itertools import product as product
+import numpy as np
+from math import ceil
+
+
+class PriorBox(object):
+    def __init__(self, cfg, image_size=None, phase='train'):
+        super(PriorBox, self).__init__()
+        self.min_sizes = cfg['min_sizes']
+        self.steps = cfg['steps']
+        self.clip = cfg['clip']
+        self.image_size = image_size
+        self.feature_maps = [[ceil(self.image_size[0]/step), ceil(self.image_size[1]/step)] for step in self.steps]
+        self.name = "s"
+
+    def forward(self):
+        anchors = []
+        for k, f in enumerate(self.feature_maps):
+            min_sizes = self.min_sizes[k]
+            for i, j in product(range(f[0]), range(f[1])):
+                for min_size in min_sizes:
+                    s_kx = min_size / self.image_size[1]
+                    s_ky = min_size / self.image_size[0]
+                    dense_cx = [x * self.steps[k] / self.image_size[1] for x in [j + 0.5]]
+                    dense_cy = [y * self.steps[k] / self.image_size[0] for y in [i + 0.5]]
+                    for cy, cx in product(dense_cy, dense_cx):
+                        anchors += [cx, cy, s_kx, s_ky]
+
+        # back to torch land
+        output = torch.Tensor(anchors).view(-1, 4)
+        if self.clip:
+            output.clamp_(max=1, min=0)
+        return output
diff --git a/Pytorch_Retinaface/models/__init__.py b/Pytorch_Retinaface/models/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/Pytorch_Retinaface/models/net.py b/Pytorch_Retinaface/models/net.py
new file mode 100644
index 0000000..beb6040
--- /dev/null
+++ b/Pytorch_Retinaface/models/net.py
@@ -0,0 +1,137 @@
+import time
+import torch
+import torch.nn as nn
+import torchvision.models._utils as _utils
+import torchvision.models as models
+import torch.nn.functional as F
+from torch.autograd import Variable
+
+def conv_bn(inp, oup, stride = 1, leaky = 0):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.LeakyReLU(negative_slope=leaky, inplace=True)
+    )
+
+def conv_bn_no_relu(inp, oup, stride):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 3, stride, 1, bias=False),
+        nn.BatchNorm2d(oup),
+    )
+
+def conv_bn1X1(inp, oup, stride, leaky=0):
+    return nn.Sequential(
+        nn.Conv2d(inp, oup, 1, stride, padding=0, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.LeakyReLU(negative_slope=leaky, inplace=True)
+    )
+
+def conv_dw(inp, oup, stride, leaky=0.1):
+    return nn.Sequential(
+        nn.Conv2d(inp, inp, 3, stride, 1, groups=inp, bias=False),
+        nn.BatchNorm2d(inp),
+        nn.LeakyReLU(negative_slope= leaky,inplace=True),
+
+        nn.Conv2d(inp, oup, 1, 1, 0, bias=False),
+        nn.BatchNorm2d(oup),
+        nn.LeakyReLU(negative_slope= leaky,inplace=True),
+    )
+
+class SSH(nn.Module):
+    def __init__(self, in_channel, out_channel):
+        super(SSH, self).__init__()
+        assert out_channel % 4 == 0
+        leaky = 0
+        if (out_channel <= 64):
+            leaky = 0.1
+        self.conv3X3 = conv_bn_no_relu(in_channel, out_channel//2, stride=1)
+
+        self.conv5X5_1 = conv_bn(in_channel, out_channel//4, stride=1, leaky = leaky)
+        self.conv5X5_2 = conv_bn_no_relu(out_channel//4, out_channel//4, stride=1)
+
+        self.conv7X7_2 = conv_bn(out_channel//4, out_channel//4, stride=1, leaky = leaky)
+        self.conv7x7_3 = conv_bn_no_relu(out_channel//4, out_channel//4, stride=1)
+
+    def forward(self, input):
+        conv3X3 = self.conv3X3(input)
+
+        conv5X5_1 = self.conv5X5_1(input)
+        conv5X5 = self.conv5X5_2(conv5X5_1)
+
+        conv7X7_2 = self.conv7X7_2(conv5X5_1)
+        conv7X7 = self.conv7x7_3(conv7X7_2)
+
+        out = torch.cat([conv3X3, conv5X5, conv7X7], dim=1)
+        out = F.relu(out)
+        return out
+
+class FPN(nn.Module):
+    def __init__(self,in_channels_list,out_channels):
+        super(FPN,self).__init__()
+        leaky = 0
+        if (out_channels <= 64):
+            leaky = 0.1
+        self.output1 = conv_bn1X1(in_channels_list[0], out_channels, stride = 1, leaky = leaky)
+        self.output2 = conv_bn1X1(in_channels_list[1], out_channels, stride = 1, leaky = leaky)
+        self.output3 = conv_bn1X1(in_channels_list[2], out_channels, stride = 1, leaky = leaky)
+
+        self.merge1 = conv_bn(out_channels, out_channels, leaky = leaky)
+        self.merge2 = conv_bn(out_channels, out_channels, leaky = leaky)
+
+    def forward(self, input):
+        # names = list(input.keys())
+        input = list(input.values())
+
+        output1 = self.output1(input[0])
+        output2 = self.output2(input[1])
+        output3 = self.output3(input[2])
+
+        up3 = F.interpolate(output3, size=[output2.size(2), output2.size(3)], mode="nearest")
+        output2 = output2 + up3
+        output2 = self.merge2(output2)
+
+        up2 = F.interpolate(output2, size=[output1.size(2), output1.size(3)], mode="nearest")
+        output1 = output1 + up2
+        output1 = self.merge1(output1)
+
+        out = [output1, output2, output3]
+        return out
+
+
+
+class MobileNetV1(nn.Module):
+    def __init__(self):
+        super(MobileNetV1, self).__init__()
+        self.stage1 = nn.Sequential(
+            conv_bn(3, 8, 2, leaky = 0.1),    # 3
+            conv_dw(8, 16, 1),   # 7
+            conv_dw(16, 32, 2),  # 11
+            conv_dw(32, 32, 1),  # 19
+            conv_dw(32, 64, 2),  # 27
+            conv_dw(64, 64, 1),  # 43
+        )
+        self.stage2 = nn.Sequential(
+            conv_dw(64, 128, 2),  # 43 + 16 = 59
+            conv_dw(128, 128, 1), # 59 + 32 = 91
+            conv_dw(128, 128, 1), # 91 + 32 = 123
+            conv_dw(128, 128, 1), # 123 + 32 = 155
+            conv_dw(128, 128, 1), # 155 + 32 = 187
+            conv_dw(128, 128, 1), # 187 + 32 = 219
+        )
+        self.stage3 = nn.Sequential(
+            conv_dw(128, 256, 2), # 219 +3 2 = 241
+            conv_dw(256, 256, 1), # 241 + 64 = 301
+        )
+        self.avg = nn.AdaptiveAvgPool2d((1,1))
+        self.fc = nn.Linear(256, 1000)
+
+    def forward(self, x):
+        x = self.stage1(x)
+        x = self.stage2(x)
+        x = self.stage3(x)
+        x = self.avg(x)
+        # x = self.model(x)
+        x = x.view(-1, 256)
+        x = self.fc(x)
+        return x
+
diff --git a/Pytorch_Retinaface/models/retinaface.py b/Pytorch_Retinaface/models/retinaface.py
new file mode 100644
index 0000000..a120889
--- /dev/null
+++ b/Pytorch_Retinaface/models/retinaface.py
@@ -0,0 +1,130 @@
+import os
+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 .net import MobileNetV1 as MobileNetV1
+from .net import FPN as FPN
+from .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', weights_path='', device="cuda"):
+        """
+        :param cfg:  Network related settings.
+        :param phase: train or test.
+        """
+        weights_path = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))), weights_path)
+
+        super(RetinaFace,self).__init__()
+        self.phase = phase
+        backbone = None
+        if cfg['name'] == 'mobilenet0.25':
+            backbone = MobileNetV1()
+            if cfg['pretrain']:
+                checkpoint = torch.load(weights_path, map_location=torch.device(device))
+                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
diff --git a/Pytorch_Retinaface/pytorch_retinaface.py b/Pytorch_Retinaface/pytorch_retinaface.py
new file mode 100644
index 0000000..8d07c1d
--- /dev/null
+++ b/Pytorch_Retinaface/pytorch_retinaface.py
@@ -0,0 +1,150 @@
+import os
+import time
+import torch
+import torch.backends.cudnn as cudnn
+import cv2
+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
+from .models.retinaface import RetinaFace
+from .utils.box_utils import decode, decode_landm
+
+class Pytorch_RetinaFace:
+    def __init__(self, cfg="mobile0.25", pretrained_path="./weights/mobilenet0.25_Final.pth", weights_path="./weights/mobilenetV1X0.25_pretrain.tar", device="cuda", vis_thres=0.6, top_k=5000, keep_top_k=750, nms_threshold=0.4, confidence_threshold=0.02):
+        self.vis_thres = vis_thres
+        self.top_k = top_k
+        self.keep_top_k = keep_top_k
+        self.nms_threshold = nms_threshold
+        self.confidence_threshold = confidence_threshold
+        self.cfg = cfg_mnet if cfg=="mobile0.25" else cfg_re50
+        self.device = torch.device(device)
+        self.net = RetinaFace(cfg=self.cfg, weights_path=weights_path, phase='test', device=device).to(self.device)
+        self.load_model_weights(pretrained_path)
+        self.net.eval()
+
+    def check_keys(self, 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(self, 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_weights(self, pretrained_path):
+        pretrained_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), pretrained_path)
+        print('Loading pretrained model from {}'.format(pretrained_path))
+        pretrained_dict = torch.load(pretrained_path, map_location=self.device)
+        if "state_dict" in pretrained_dict.keys():
+            pretrained_dict = self.remove_prefix(pretrained_dict['state_dict'], 'module.')
+        else:
+            pretrained_dict = self.remove_prefix(pretrained_dict, 'module.')
+        self.check_keys(self.net, pretrained_dict)
+        self.net.load_state_dict(pretrained_dict, strict=False)
+        self.net.to(self.device)
+        return self.net
+
+    def center_and_crop_rescale(self, image, dets, scale_factor=4, shift_factor=0.35):
+        cropped_imgs = []
+        for index, bbox in enumerate(dets):
+            if bbox[4] < self.vis_thres:
+                continue
+
+            x1, y1, x2, y2 = map(int, bbox[:4])
+            face_width = x2 - x1
+            face_height = y2 - y1
+
+            # New height and width based on scale factor
+            new_face_height = int(face_height * scale_factor)
+            new_face_width = int(new_face_height * (face_width / face_height))
+
+            # Center coordinates of the detected face
+            center_x = x1 + face_width // 2
+            center_y = y1 + face_height // 2 + int(new_face_height * (0.5 - shift_factor))
+
+            # Crop coordinates, adjusted to the image boundaries
+            crop_x1 = max(0, center_x - new_face_width // 2)
+            crop_x2 = min(image.shape[1], center_x + new_face_width // 2)
+            crop_y1 = max(0, center_y - new_face_height // 2)
+            crop_y2 = min(image.shape[0], center_y + new_face_height // 2)
+
+            # Crop the region and add padding to form a square
+            cropped_imgs.append(image[crop_y1:crop_y2, crop_x1:crop_x2])
+        return cropped_imgs
+
+    def detect_faces(self, img):
+        resize = 1
+
+        if len(img.shape) == 4 and img.shape[0] == 1:
+            img = torch.squeeze(img, 0)
+        if isinstance(img, np.ndarray):
+            img = torch.from_numpy(img)
+        img = img.to(self.device)
+
+        im_height, im_width, _ = img.shape
+        scale = torch.Tensor([img.shape[1], img.shape[0], img.shape[1], img.shape[0]])
+        mean_values = torch.tensor([104, 117, 123], dtype=torch.float32).to(self.device)
+        mean_values = mean_values.view(1, 1, 3)
+        img -= mean_values
+        img = img.permute(2, 0, 1)
+        img = img.unsqueeze(0)
+        scale = scale.to(self.device)
+
+        tic = time.time()
+        with torch.no_grad():
+            loc, conf, landms = self.net(img)  # forward pass
+        print('net forward time: {:.4f}'.format(time.time() - tic))
+
+        priorbox = PriorBox(self.cfg, image_size=(im_height, im_width))
+        priors = priorbox.forward()
+        priors = priors.to(self.device)
+        prior_data = priors.data
+        boxes = decode(loc.data.squeeze(0), prior_data, self.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, self.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(self.device)
+        landms = landms * scale1 / resize
+        landms = landms.cpu().numpy()
+
+        # Ignore low scores
+        inds = np.where(scores > self.confidence_threshold)[0]
+        boxes = boxes[inds]
+        landms = landms[inds]
+        scores = scores[inds]
+
+        # Keep top-K before NMS
+        order = scores.argsort()[::-1][:self.top_k]
+        boxes = boxes[order]
+        landms = landms[order]
+        scores = scores[order]
+
+        # Perform NMS
+        dets = np.hstack((boxes, scores[:, np.newaxis])).astype(np.float32, copy=False)
+        keep = py_cpu_nms(dets, self.nms_threshold)
+        dets = dets[keep, :]
+        landms = landms[keep]
+
+        # Keep top-K faster NMS
+        dets = dets[:self.keep_top_k, :]
+        landms = landms[:self.keep_top_k, :]
+
+        dets = np.concatenate((dets, landms), axis=1)
+        return dets
diff --git a/Pytorch_Retinaface/utils/__init__.py b/Pytorch_Retinaface/utils/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/Pytorch_Retinaface/utils/box_utils.py b/Pytorch_Retinaface/utils/box_utils.py
new file mode 100644
index 0000000..c1d12bc
--- /dev/null
+++ b/Pytorch_Retinaface/utils/box_utils.py
@@ -0,0 +1,330 @@
+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
+
+
diff --git a/Pytorch_Retinaface/utils/nms/__init__.py b/Pytorch_Retinaface/utils/nms/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/Pytorch_Retinaface/utils/nms/py_cpu_nms.py b/Pytorch_Retinaface/utils/nms/py_cpu_nms.py
new file mode 100644
index 0000000..54e7b25
--- /dev/null
+++ b/Pytorch_Retinaface/utils/nms/py_cpu_nms.py
@@ -0,0 +1,38 @@
+# --------------------------------------------------------
+# 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
diff --git a/Pytorch_Retinaface/weights/mobilenet0.25_Final.pth b/Pytorch_Retinaface/weights/mobilenet0.25_Final.pth
new file mode 100644
index 0000000..a02809f
Binary files /dev/null and b/Pytorch_Retinaface/weights/mobilenet0.25_Final.pth differ
diff --git a/Pytorch_Retinaface/weights/mobilenetV1X0.25_pretrain.tar b/Pytorch_Retinaface/weights/mobilenetV1X0.25_pretrain.tar
new file mode 100644
index 0000000..cb53f82
Binary files /dev/null and b/Pytorch_Retinaface/weights/mobilenetV1X0.25_pretrain.tar differ
diff --git a/README.md b/README.md
index 0e8fd3c..63f4d0d 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,4 @@
 # ComfyUI-AutoCropFaces
 Use RetinaFace to detect and automatically crop faces
+
+Forked and modified from [biubug6/Pytorch_Retinaface](https://github.com/biubug6/Pytorch_Retinaface)
diff --git a/__init__.py b/__init__.py
new file mode 100644
index 0000000..72b0a92
--- /dev/null
+++ b/__init__.py
@@ -0,0 +1,69 @@
+import torch
+from .Pytorch_Retinaface.pytorch_retinaface import Pytorch_RetinaFace
+
+class AutoCropFaces:
+    def __init__(self):
+        pass
+    
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "image": ("IMAGE",),
+                "max_number_of_faces": ("INT", {
+                    "default": 5, 
+                    "min": 1,
+                    "max": 50,
+                    "step": 1,
+                }),
+                "index_of_face": ("INT", {
+                    "default": 1,
+                    "min": 1,
+                    "step": 1,
+                    "display": "number"
+                }),
+                "scale_factor": ("FLOAT", {
+                    "default": 4,
+                    "min": 0.5,
+                    "max": 10,
+                    "step": 0.5,
+                    "display": "slider"
+                }),
+                "shift_factor": ("FLOAT", {
+                    "default": 0.3,
+                    "min": 0,
+                    "max": 1,
+                    "step": 0.1,
+                    "display": "slider"
+                })
+            },
+        }
+
+    RETURN_TYPES = ("IMAGE",)
+    RETURN_NAMES = ("face",)
+
+    FUNCTION = "auto_crop_faces"
+
+    CATEGORY = "Faces"
+
+    def auto_crop_faces(self, image, max_number_of_faces, index_of_face, scale_factor, shift_factor):
+        #TODO: currently only support one single image. No batch.
+        image_without_batch = image[0]
+        image_255 = image_without_batch * 255
+        rf = Pytorch_RetinaFace(top_k=50, keep_top_k=max_number_of_faces)
+        dets = rf.detect_faces(image_255)
+        cropped_images = rf.center_and_crop_rescale(image_without_batch, dets, scale_factor=scale_factor, shift_factor=shift_factor)
+        if len(cropped_images)>=1:
+            clamped_index = max(1, min(index_of_face, len(cropped_images)))
+            cropped_image = torch.unsqueeze(cropped_images[clamped_index-1], 0)
+            return (cropped_image,)
+        return (image,)
+
+NODE_CLASS_MAPPINGS = {
+    "AutoCropFaces": AutoCropFaces
+}
+
+# A dictionary that contains the friendly/humanly readable titles for the nodes
+NODE_DISPLAY_NAME_MAPPINGS = {
+    "AutoCropFaces": "Auto Crop Faces"
+}
diff --git a/test.py b/test.py
new file mode 100644
index 0000000..2cb01f8
--- /dev/null
+++ b/test.py
@@ -0,0 +1,46 @@
+from __future__ import print_function
+import os
+import argparse
+import numpy as np
+import cv2
+from Pytorch_Retinaface.pytorch_retinaface import Pytorch_RetinaFace
+
+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('--cpu', action="store_true", default=False, help='Use cpu inference')
+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=True, help='show detection results')
+parser.add_argument('--vis_thres', default=0.6, type=float, help='visualization_threshold')
+args = parser.parse_args()
+
+
+def main():
+    rf = Pytorch_RetinaFace()
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    output_dir = os.path.join(current_dir, "./Pytorch_Retinaface/outputs")
+
+    image_path = os.path.join(current_dir, "./Pytorch_Retinaface/images/test.webp")
+    if not os.path.exists(image_path):
+        raise FileNotFoundError
+    img_raw = cv2.imread(image_path, cv2.IMREAD_COLOR)
+
+    img = np.float32(img_raw)
+
+    dets = rf.detect_faces(img)
+
+    # Crop and save each detected face
+    cropped_imgs = rf.center_and_crop_rescale(img_raw, dets)
+    for index, cropped_img in enumerate(cropped_imgs):
+        # Save the final image
+        os.makedirs(output_dir, exist_ok=True)
+        cv2.imwrite(os.path.join(output_dir, f"cropped_face_{index}.jpg"), cropped_img)
+        print(f"Saved: cropped_face_{index}.jpg")
+
+if __name__ == '__main__':
+    main()
\ No newline at end of file