Upload 2 files

Use Yolov8 OBB trained model

app.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[ ]:
+
+
+from ultralytics import YOLO
+from PIL import Image, ImageDraw, ImageFont
+import gradio as gr
+from huggingface_hub import snapshot_download
+import os
+import numpy as np
+
+# Best Yolov8 trained model
+best_yolo_model = "best.pt"
+
+def load_model(repo_id):
+    download_dir = snapshot_download(repo_id)
+    print(download_dir)
+    path  = os.path.join(download_dir, "best_int8_openvino_model")
+    print(path)
+    detection_model = YOLO(path, task='detect')
+    return detection_model
+
+
+def predict(pilimg):
+ 
+    detection_model = YOLO(best_yolo_model, task='detect')
+    
+    result = detection_model.predict(pilimg, conf=0.4, iou=0.5)
+    #result = detection_model.predict(pilimg)
+        
+    obb = result[0].obb
+    confs = obb.conf
+    #print("obb : ", obb)
+    #print( confidence : ", confs)
+              
+    img_bgr = result[0].plot()
+    out_pilimg = Image.fromarray(img_bgr[..., ::-1])  # RGB-order PIL image
+   
+    # Show warning if no object is detected
+    if len(result[0].obb.cls) == 0:
+        gr.Warning("No object detected!")   
+         
+    return out_pilimg
+
+
+REPO_ID = "ITI107-2024S2/8035531F"
+#detection_model = load_model(REPO_ID)
+
+title = "Detect Durian and Mangosteen (King and Queen of Fruits) In The Image"
+interface = gr.Interface(
+                fn=predict,
+                inputs=gr.Image(type="pil", label="Input Image"),
+                outputs=gr.Image(type="pil", label="Object Detection With Confidence Level"),
+                title=title,
+             )
+
+# Launch the interface
+interface.launch(share=True)
+
+
+# In[ ]:
+
+
+
+

best.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e9b98469c201e61f3d6f552273a7188b95158ed2d4c286af84f5f6949af4e1
-size 23557388
+oid sha256:8cff4c640a5a463493e4b2b2bba77942376d94a85c2b2824f18b73240b91ae45
+size 23574796