# Install Essential Libraries

$!$pip install ultralytics

import numpy as np # linear algebra

import pandas as pd # data processing, CSV file I$/$O $($e$.$g$.$ pd$.$read$\_$csv$)$

# Input data files are available in the read$-$only $"../$input$/"$ directory

# For example, running this $($by clicking run or pressing Shift$+$Enter$)$ will list all files under the input directory

import os

for dirname, $\_,$ filenames in os$.$walk$(\text{'}/$kaggle$/$input$\text{'})$:

for filename in filenames:

os$.$path.join$($dirname$,$ filename$)$

from google.colab import drive

# Mount Google Drive

drive.mount$(\text{'}/$content$/$drive$\text{'})$

# Example folder path in Google Drive

Drowsy$=\text{'}/$content$/$drive$/$My Drive$/$DDD$/$Drowsy$/$Drowsy$\text{'}$

Non$\_$Drowsy$=\text{'}/$content$/$drive$/$My Drive$/$DDD$/$NonDrowsy$/$NonDrowsy$\text{'}$

# List all files in the folder

Path$1=$ os$.$listdir$($Drowsy$)$

Path$2=$ os$.$listdir$($Non$\_$Drowsy$)$

filepaths $=[]$

labels $=[]$

for file in drowsy$\_$files:

filepath $=$ os$.$path.join$($Drowsy$,$ file$)$

filepaths.append$($filepath$)$

labels.append$(\text{'}$drowsy$\text{'})$

# Iterate through non$-$drowsy images and add file paths and labels

for file in non$\_$drowsy$\_$files:

filepath $=$ os$.$path.join$($Non$\_$Drowsy, file$)$

filepaths.append$($filepath$)$

labels.append$(\text{'}$non$-$drowsy'$)$

df $=$ pd$.$DataFrame$(\{\text{'}$filepaths$\text{'}$: filepaths, 'labels': labels$\})$

# Print the number of images in each category

print$($df$[\text{'}$labels$\text{'}].$value$\_$counts$())$

# Print the DataFrame shape

print$($df$.$shape$)$

# Print a sample of the DataFrame

print$($df$.$sample$(10))$

import os

import pandas as pd

dict$\_$list $=[$Drowsy$,$Non$\_$Drowsy$]$

for i$,$ j in enumerate$($dict$\_$list$)$:

flist $=$ os$.$listdir$($j$)$

for f in flist:

fpath $=$ os$.$path.join$($j$,$ f$)$

filepaths.append$($fpath$)$

if i $==0$:

labels.append$(\text{'}$Drowsy$\text{'})$

elif i $==1$:

labels.append$(\text{'}$Non$\_$Drowsy'$)$

Fseries $=$ pd$.$Series$($filepaths$,$ name$=$"filepaths"$)$

Lseries $=$ pd$.$Series$($labels$,$ name$=$"labels"$)$

bc$\_$data $=$ pd$.$concat$([$Fseries$,$ Lseries$],$ axis$=1)$

bc$\_$df $=$ pd$.$DataFrame$($bc$\_$data$)$

print$($bc$\_$df$["$labels$"].$value$\_$counts$())$

print$($bc$\_$df$.$shape$)$

bc$\_$df$.$sample$(10)$

from sklearn.model$\_$selection import train$\_$test$\_$split

# Assuming bc$\_$df is your DataFrame containing the data

train$\_$images, test$\_$images $=$ train$\_$test$\_$split$($bc$\_$df$,$ test$\_$size$=0\mathrm{.}3,$ random$\_$state$=42)$

train$\_$set, val$\_$set $=$ train$\_$test$\_$split$($bc$\_$df$,$ test$\_$size$=0\mathrm{.}2,$ random$\_$state$=42)$

#Generate batches of tensor image data with real$-$time data augmentation.

import tensorflow as tf

from tensorflow.keras.preprocessing.image import ImageDataGenerator

# Assuming you have imported pandas and numpy as well

# Your code for generating image data batches

image$\_$gen $=$ ImageDataGenerator$($preprocessing$\_$function$=$tf$.$keras.applications.mobilenet$\_$v$2.$preprocess$\_$input$)$

train $=$ image$\_$gen.flow$\_$from$\_$dataframe$($dataframe$=$train$\_$set, x$\_$col$=$"filepaths", y$\_$col$=$"labels",

target$\_$size$=(244,244),$

color$\_$mode$=\text{'}$rgb$\text{'},$

class$\_$mode$=$"categorical",

batch$\_$size$=32,$

shuffle$=$False$)$

test $=$ image$\_$gen.flow$\_$from$\_$dataframe$($dataframe$=$test$\_$images, x$\_$col$=$"filepaths", y$\_$col$=$"labels",

target$\_$size$=(244,244),$

color$\_$mode$=\text{'}$rgb$\text{'},$

class$\_$mode$=$"categorical",

batch$\_$size$=32,$

shuffle$=$False$)$

val $=$ image$\_$gen.flow$\_$from$\_$dataframe$($dataframe$=$val$\_$set, x$\_$col$=$"filepaths", y$\_$col$=$"labels",

target$\_$size$=(244,244),$

color$\_$mode$=\text{'}$rgb$\text{'},$

class$\_$mode$=$"categorical",

batch$\_$size$=32,$

shuffle$=$False$)$

classes$=$list$($train$.$class$\_$indices.keys$())$

print $($classes$)$

import matplotlib.pyplot as plt

import numpy as np

def bc$\_$images$($image$\_$gen$)$:

images, labels $=$ next$($image$\_$gen$)$ # get a sample batch from the generator

plt$.$figure$($figsize$=(20,20))$

length $=$ len$($labels$)$

if length $<25$:

r $=$ length

else:

r $=25$

for i in range$($r$)$:

plt$.$subplot$(5,5,$ i $+1)$

image $=($images$[$i$]+1)/2$ # scale images between $0$ and $1$

plt$.$imshow$($image$)$

plt$.$title$($np$.$argmax$($labels$[$i$]),$ color$=$"green", fontsize$=16)$

plt$.$axis$(\text{'}$off$\text{'})$

plt$.$show$()$

bc$\_$images$($train$)$

from ultralytics import YOLO

import PIL

from PIL import Image

from IPython.display import display

import os

import pathlib

model $=$ YOLO$("$yolov$8$m$.$pt$")$

results$=$model.predict$($source$="/$content$/$drive$/$My Drive$/$DDD$/$Drowsy$/$Drowsy$/$X$1346.$png$",$

save$=$True, conf$=0\mathrm{.}2,$iou$=0\mathrm{.}5)$

result $=$ results$[0]$

box $=$ result.boxes$[0]$

for result in results:

boxes $=$ result.boxes # Boxes object for bbox outputs

masks $=$ result.masks # Masks object for segmentation masks outputs

probs $=$

can you give the driver's drowsiness detection using YOLOv$8$