Update app.py

app.py

@@ -1,16 +1,16 @@
 import gradio as gr
 import tensorflow as tf
 import numpy as np
-import cv2
 from PIL import Image
 import io
+import moviepy.editor as mp
 
 # Load a pre-trained TensorFlow model (replace with your model path)
 model = tf.keras.applications.MobileNetV2(weights="imagenet")
 
 def preprocess_image(image):
     img = np.array(image)
-    img = cv2.resize(img, (224, 224))
+    img = tf.image.resize(img, (224, 224))
     img = tf.keras.applications.mobilenet_v2.preprocess_input(img)
     return np.expand_dims(img, axis=0)
 
@@ -20,27 +20,21 @@ def classify_frame(frame):
     decoded_predictions = tf.keras.applications.mobilenet_v2.decode_predictions(predictions, top=1)[0]
     return decoded_predictions[0][1]
 
-def process_video(video):
+def process_video(video_file):
     result = ""
-    cap = cv2.VideoCapture(video)
-    frame_count = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
-    frame_interval = frame_count // 10  # Analyze 10 frames evenly spaced throughout the video
-
-    for i in range(0, frame_count, frame_interval):
-        cap.set(cv2.CAP_PROP_POS_FRAMES, i)
-        ret, frame = cap.read()
-        if not ret:
-            break
+    video = mp.VideoFileClip(io.BytesIO(video_file.read()))
+    duration = int(video.duration)
+    frame_interval = duration // 10  # Analyze 10 frames evenly spaced throughout the video
 
-        frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-        image = Image.fromarray(frame_rgb)
+    for i in range(0, duration, frame_interval):
+        frame = video.get_frame(i)
+        image = Image.fromarray(frame)
         label = classify_frame(image)
         
         if "baseball" in label.lower():
             result = "The runner is out"
             break
 
-    cap.release()
     if result == "":
         result = "The runner is safe"