diff --git a/087_DeepSort/download.sh b/087_DeepSort/download.sh
new file mode 100755
index 0000000000..1648c4c412
--- /dev/null
+++ b/087_DeepSort/download.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+
+curl -sc /tmp/cookie "https://drive.google.com/uc?export=download&id=1CIAU0OQL4bFIms-e74V2OUYnqIzq10q-" > /dev/null
+CODE="$(awk '/_warning_/ {print $NF}' /tmp/cookie)"
+curl -Lb /tmp/cookie "https://drive.google.com/uc?export=download&confirm=${CODE}&id=1CIAU0OQL4bFIms-e74V2OUYnqIzq10q-" -o resources.tar.gz
+tar -zxvf resources.tar.gz
+rm resources.tar.gz
+
+echo Download finished.
diff --git a/087_DeepSort/feature_extractor.py b/087_DeepSort/feature_extractor.py
new file mode 100644
index 0000000000..7e46c5830b
--- /dev/null
+++ b/087_DeepSort/feature_extractor.py
@@ -0,0 +1,60 @@
+import torch
+import torchvision.transforms as transforms
+import numpy as np
+import cv2
+import logging
+
+from .model import Net
+
+
+class Extractor(object):
+    def __init__(self, model_path, use_cuda=True):
+        self.net = Net(reid=True)
+        self.device = "cuda" if torch.cuda.is_available() and use_cuda else "cpu"
+        print('@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ model_path:', model_path)
+        state_dict = torch.load(model_path, map_location=lambda storage, loc: storage)['net_dict']
+        self.net.load_state_dict(state_dict)
+
+        logger = logging.getLogger("root.tracker")
+        logger.info("Loading weights from {}... Done!".format(model_path))
+        self.net.to(self.device)
+        self.size = (64, 128)
+        self.norm = transforms.Compose([
+            transforms.ToTensor(),
+            transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
+        ])
+
+    def _preprocess(self, im_crops):
+        """
+        TODO:
+            1. to float with scale from 0 to 1
+            2. resize to (64, 128) as Market1501 dataset did
+            3. concatenate to a numpy array
+            3. to torch Tensor
+            4. normalize
+        """
+        def _resize(im, size):
+            return cv2.resize(im.astype(np.float32)/255., size)
+
+        im_batch = torch.cat([self.norm(_resize(im, self.size)).unsqueeze(
+            0) for im in im_crops], dim=0).float()
+        return im_batch
+
+    def __call__(self, im_crops):
+        im_batch = self._preprocess(im_crops)
+        with torch.no_grad():
+            im_batch = im_batch.to(self.device)
+            features = self.net(im_batch)
+
+            ################################################################################################
+            torch.onnx.export(self.net, im_batch, 'deepsort_128x64.onnx', verbose=True, opset_version=12)
+            ################################################################################################
+
+        return features.cpu().numpy()
+
+
+if __name__ == '__main__':
+    img = cv2.imread("demo.jpg")[:, :, (2, 1, 0)]
+    extr = Extractor("checkpoint/ckpt.t7")
+    feature = extr(img)
+    print(feature.shape)
diff --git a/087_DeepSort/url.txt b/087_DeepSort/url.txt
new file mode 100644
index 0000000000..ff193dde01
--- /dev/null
+++ b/087_DeepSort/url.txt
@@ -0,0 +1,2 @@
+https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch
+https://github.com/PINTO0309/openvino2tensorflow
\ No newline at end of file