Update app.py

app.py

@@ -1,23 +1,37 @@
-import cv2
-from streamlit_webrtc import VideoTransformerBase, webrtc_streamer
+import streamlit as st
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+from PIL import Image
+import requests
 
-faceCascade = cv2.CascadeClassifier(cv2.haarcascades+'haarcascade_frontalface_default.xml')
+# 加载模型和处理器
+processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten")
+model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
 
+def load_image(image_file):
+    img = Image.open(image_file)
+    return img
 
-class VideoTransformer(VideoTransformerBase):
-    def __init__(self):
-        self.i = 0
+def predict(image):
+    # 处理图片
+    pixel_values = processor(images=image, return_tensors="pt").pixel_values
+    # 生成预测
+    output_ids = model.generate(pixel_values)
+    # 转换输出文本
+    output_text = processor.decode(output_ids[0], skip_special_tokens=True)
+    return output_text
 
-    def transform(self, frame):
-        img = frame.to_ndarray(format="bgr24")
-        gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
-        faces = faceCascade.detectMultiScale(gray, 1.3, 5)
-        i =self.i+1
-        for (x, y, w, h) in faces:
-            cv2.rectangle(img, (x, y), (x + w, y + h), (95, 207, 30), 3)
-            cv2.rectangle(img, (x, y - 40), (x + w, y), (95, 207, 30), -1)
-            cv2.putText(img, 'F-' + str(i), (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (0, 0, 0), 2)
+def main():
+    st.title("图片物体识别")
+    image_file = st.file_uploader("上传一张图片", type=["jpg", "png", "jpeg"])
 
-        return img
+    if image_file is not None:
+        # 显示图片
+        image = load_image(image_file)
+        st.image(image, caption='上传的图片', use_column_width=True)
+        # 预测图片
+        if st.button("识别图片"):
+            result_text = predict(image)
+            st.write(f"识别结果: {result_text}")
 
-webrtc_streamer(key="example", video_transformer_factory=VideoTransformer)
+if __name__ == '__main__':
+    main()