updates

app.py

@@ -0,0 +1,58 @@
+
+import matplotlib.pyplot as plt
+import streamlit as st
+from PIL import Image
+import numpy as np
+import torch
+import cv2
+
+
+@st.cache_resource
+def load_model():
+    model = torch.hub.load(
+        'ultralytics/yolov5', 
+        'custom', 
+        path='best.pt'
+    )
+    return model
+model = load_model()
+
+
+def make_prediction(img_path):
+    img = Image.open(img_path).convert('RGB')
+    open_cv_image = np.array(img)
+    open_cv_image = open_cv_image[:, :, ::-1].copy()
+    results = model([open_cv_image])
+    return open_cv_image, results
+
+
+def show_bounding_boxes(img, results, cls):
+    df = results.pandas().xyxy[0]
+    df = df[df['name'] == cls]
+    list_of_rows = [list(row) for row in df.values]
+
+    for each_row in list_of_rows:
+        cv2.rectangle(img, 
+            (int(each_row[0]), int(each_row[1])), 
+            (int(each_row[2]), int(each_row[3])), 
+            (255, 0, 0), 2
+        )
+    return img
+
+
+st.title("Object Detection :tea: :coffee:")
+upload = st.file_uploader(label= "Upload an image : ", type = ["png","jpg","jpeg"])
+
+if upload:
+    print(upload)
+    img, results = make_prediction(upload)
+    bounded_img = show_bounding_boxes(img, results, 'Table')
+    fig = plt.figure(figsize=(12,12))
+    ax = fig.add_subplot(111)
+    plt.imshow(bounded_img)
+    plt.xticks([],[])
+    plt.yticks([],[])
+    ax.spines[["top","bottom","right","left"]].set_visible(False)
+
+    st.pyplot(fig,use_container_width=True)
+

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79701412b026fe2f832231ae02777540ff18a932c491b2b87b0b5411a48aba5
+size 93836445

requirements.txt

@@ -0,0 +1,6 @@
+numpy==1.24.4
+opencv-python==4.8.1.78
+pandas==2.0.3
+streamlit==1.29.0
+torch==2.1.1
+ultralytics==8.0.221