diff --git a/README.md b/README.md
index dd1fa22..b32db3e 100644
--- a/README.md
+++ b/README.md
@@ -30,11 +30,12 @@ https://user-images.githubusercontent.com/37156032/160282244-42f6bd8c-bfc8-47af-
     <li>Clone this repo</li>
     <li>Install all the dependencies</li>
     <li>Download deepsort <a href="https://drive.google.com/drive/folders/1xhG0kRH1EX5B9_Iz8gQJb7UNnn_riXi6">checkpoint</a> file and paste it in deep_sort_pytorch/deep_sort/deep/checkpoint</li>
-    <li>Run -> streamlit run app.py</li>
+    <li>Run -> 'streamlit run app.py' or 'python -m streamlit run app.py' in Windows.</li>
 </ol>
 
 ## :star: Recent changelog
 <ol>
+    <li>Fixed the errors related to <a href="https://numpy.org/devdocs/release/1.20.0-notes.html#deprecations">Numpy 1.20.0 alias deprecations.</a></li>
     <li>Updated yolov5s weight file name in detect() in app.py</li>
     <li>Added drive link to download DeepSort checkpoint file (45Mb).</li>
 </ol>
diff --git a/deep_sort_pytorch/deep_sort/deep_sort.py b/deep_sort_pytorch/deep_sort/deep_sort.py
index adb7d93..a856f5f 100644
--- a/deep_sort_pytorch/deep_sort/deep_sort.py
+++ b/deep_sort_pytorch/deep_sort/deep_sort.py
@@ -47,7 +47,7 @@ def update(self, bbox_xywh, confidences, ori_img):
             box = track.to_tlwh()
             x1, y1, x2, y2 = self._tlwh_to_xyxy(box)
             track_id = track.track_id
-            outputs.append(np.array([x1, y1, x2, y2, track_id], dtype=np.int))
+            outputs.append(np.array([x1, y1, x2, y2, track_id], dtype=np.int32))
         if len(outputs) > 0:
             outputs = np.stack(outputs, axis=0)
         return outputs
diff --git a/deep_sort_pytorch/deep_sort/sort/detection.py b/deep_sort_pytorch/deep_sort/sort/detection.py
index 5c884bb..e598da8 100644
--- a/deep_sort_pytorch/deep_sort/sort/detection.py
+++ b/deep_sort_pytorch/deep_sort/sort/detection.py
@@ -27,7 +27,7 @@ class Detection(object):
     """
 
     def __init__(self, tlwh, confidence, feature):
-        self.tlwh = np.asarray(tlwh, dtype=np.float)
+        self.tlwh = np.asarray(tlwh, dtype=np.float32)
         self.confidence = float(confidence)
         self.feature = np.asarray(feature, dtype=np.float32)