Spaces:
Runtime error
Runtime error
File size: 3,132 Bytes
761f4da 96705f2 2587bd0 96705f2 a52b576 0c2700d 761f4da 54c1660 761f4da 0c2700d 96705f2 0c2700d 96705f2 0c2700d 96705f2 9e3243b 96705f2 761f4da 96705f2 761f4da 96705f2 c8aa6df 35d42b9 f97c524 96705f2 0c2700d 78eae32 0b0c34c 96705f2 0c2700d 761f4da 0c2700d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 |
import gradio as gr
import os
import cv2
import face_recognition
from fastai.vision.all import load_learner
import time
import chardet
import base64
import pathlib
temp = pathlib.PosixPath
pathlib.PosixPath = pathlib.WindowsPath
model = load_learner("gaze-recognizer-v1.pkl")
def video_processing(video_file, encoded_video):
if encoded_video != "":
decoded_file_data = base64.b64decode(encoded_video)
with open("temp_video.mp4", "wb") as f:
f.write(decoded_file_data)
video_file = "temp_video.mp4"
start_time = time.time()
video_capture = cv2.VideoCapture(video_file)
on_camera = 0
off_camera = 0
total = 0
while True:
# Read a single frame from the video
for i in range(24*3):
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)
# 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
try:
# your processing code here
gaze_percentage = on_camera / total * 100
except Exception as e:
print(f"An error occurred while processing the video: {e}")
gaze_percentage = f'no face detected Total = {total},on_camera = {on_camera},off_camera = {off_camera}'
print(f'Total = {total},on_camera = {on_camera},off_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}')
if os.path.exists("temp_video.mp4"):
os.remove("temp_video.mp4")
print(gaze_percentage)
return str(gaze_percentage)
demo = gr.Interface(fn=video_processing,
inputs=["video", "text"],
outputs="text")
if __name__ == "__main__":
demo.launch() |