Update app.py

app.py

@@ -3,10 +3,10 @@ import cv2
 import numpy as np
 from ultralytics import YOLO
 
-# Load YOLO model
-model = YOLO('yolo11s-earth.pt')  # Load your model
+# 加载YOLO模型
+model = YOLO('yolo11s-earth.pt')  # 加载你的模型
 
-# Default classes
+# 默认类别
 default_classes = [
     'airplane', 'airport', 'baseballfield', 'basketballcourt', 'bridge',
     'chimney', 'dam', 'Expressway-Service-area', 'Expressway-toll-station',
@@ -16,29 +16,24 @@ default_classes = [
 ]
 
 def process_frame(frame, classes_input):
-    # Process user input classes
-    if classes_input and classes_input.strip():
+    # 将输入的类别字符串转为列表
+    if classes_input:
         classes_list = [cls.strip() for cls in classes_input.split(',')]
-        model.set_classes(classes_list)  # Set model classes
+        model.set_classes(classes_list)  # 设置模型的类别
     else:
-        # Use default classes if no input or input is empty
+        # 如果没有输入，则使用默认类别
         model.set_classes(default_classes)
     
-    # Copy frame to a writable array
+    # 复制帧为可写数组
     frame = frame.copy()
     
-    # Resize image to speed up processing (optional)
-    h, w = frame.shape[:2]
-    new_size = (640, int(h * (640 / w))) if w > h else (int(w * (640 / h)), 640)
-    resized_frame = cv2.resize(frame, new_size)
+    # 转换图像格式
+    rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
     
-    # Convert image format
-    rgb_frame = cv2.cvtColor(resized_frame, cv2.COLOR_BGR2RGB)
+    # 使用模型进行检测
+    results = model.predict(rgb_frame, imgsz=800)
     
-    # Use model for detection
-    results = model.predict(rgb_frame)
-    
-    # Draw detection results
+    # 绘制检测结果
     for result in results:
         boxes = result.boxes
         for box in boxes:
@@ -47,26 +42,20 @@ def process_frame(frame, classes_input):
             cls = box.cls[0]
             class_name = model.names[int(cls)]
             
-            # Adjust coordinates to original image size
-            x1 = int(x1 * w / new_size[0])
-            y1 = int(y1 * h / new_size[1])
-            x2 = int(x2 * w / new_size[0])
-            y2 = int(y2 * h / new_size[1])
-            
-            # Draw bounding box and label
-            cv2.rectangle(frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
-            cv2.putText(frame, f'{class_name}:{conf:.2f}', (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)
+            # 绘制边界框和标签
+            cv2.rectangle(frame, (int(x1), int(y1)), (int(x2), int(y2)), (0, 255, 0), 2)
+            cv2.putText(frame, f'{class_name}:{conf:.2f}', (int(x1), int(y1) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (36, 255, 12), 2)
     
     return frame
 
 def main():
-    # Create Gradio interface
+    # 创建Gradio界面
     with gr.Blocks() as demo:
-        gr.Markdown("# YOLO11s-Earth open vocabulary detection (DIOR finetuning)")
+        gr.Markdown("# YOLOv11s-Earth 实时检测")
         with gr.Row():
-            cam_input = gr.Image(type="numpy", sources=["webcam"], streaming=True, label="Webcam")
-            classes_input = gr.Textbox(label="New classes (comma-separated)", placeholder="e.g.: airplane, airport, tennis court")
-        output = gr.Image(label="Results", type="numpy", height=480)  # Set height to 480
+            cam_input = gr.Image(type="numpy", sources=["webcam"], streaming=True, label="摄像头输入")
+            classes_input = gr.Textbox(label="输入类别（逗号分隔）", placeholder="例如：0,1,2")
+        output = gr.Image(label="检测结果", type="numpy")
         
         cam_input.stream(
             process_frame,
@@ -74,7 +63,7 @@ def main():
             outputs=output
         )
     
-    # Launch Gradio app
+    # 启动Gradio应用
     demo.launch()
 
 if __name__ == "__main__":