added video processing

app.py

@@ -1,12 +1,73 @@
 import gradio as gr
 import os
+import cv2
+import face_recognition
+from fastai.vision.all import *
+import time
 
+version = 1
+model_path = f'models/gaze-recognizer-v{version}.pkl'
 
-def video_identity(video):
-    return video
+def video_processing(video):
+    start_time = time.time()
+    # Loop through the frames of the video
+    model = load_learner(model_path)
+    video_capture = cv2.VideoCapture(video)
+    on_camera = 0
+    off_camera = 0
+    total = 0
+    while True:
+        # Read a single frame from the video
+        for i in range(24*30):
+            ret, frame = video_capture.read()
+            if not ret:
+                break
 
+        # If there are no more frames, break out of the loop
+        if not ret:
+            break
+        
+        # Convert the frame to RGB color (face_recognition uses RGB)
+        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
+        
 
-demo = gr.Interface(video_identity,
+        # Find all the faces in the frame using a pre-trained convolutional neural network.
+        face_locations = face_recognition.face_locations(gray)
+        #face_locations = face_recognition.face_locations(gray, number_of_times_to_upsample=0, model="cnn")
+
+        if len(face_locations) > 0:
+            # Show the original frame with face rectangles drawn around the faces
+            for top, right, bottom, left in face_locations:
+                # cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255), 2)
+                face_image = gray[top:bottom, left:right]
+
+                # Resize the face image to the desired size
+                resized_face_image = cv2.resize(face_image, (128,128))
+
+                # Predict the class of the resized face image using the model
+                result = model.predict(resized_face_image)
+                print(result[0])
+                if(result[0] == 'on_camera'): on_camera = on_camera + 1
+                elif(result[0] == 'off_camera'): off_camera = off_camera + 1
+                total = total + 1
+            
+        # cv2.imshow('Video', frame)
+
+        # If the user presses the 'q' key, exit the loop
+        # if cv2.waitKey(1) & 0xFF == ord('q'):
+        #     break
+    gaze_percentage = on_camera/total*100
+    # print(total,on_camera,off_camera)
+    # print(f'focus perfectage = {on_camera/total*100}')
+    # Release the video capture object and close all windows
+    video_capture.release()
+    cv2.destroyAllWindows()
+    end_time = time.time()
+    print(f'Time taken: {end_time-start_time}')
+    return gaze_percentage
+
+
+demo = gr.Interface(fn = video_processing,
                     inputs= gr.Video(),
                     outputs = gr.Text()
                     )

models/gaze-recognizer-v1.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f553b719d666374b7fd46f7df5310561bb3520d4fb0dcc7cf523b23d87caebe
+size 87465936