Basic steps required for Computer Vision Machine Learning

Step 1 : Install the below packages:

!pip install tensorflow[and-cuda] scikit-learn==1.6.1 opencv-python==4.12.0.88 seaborn==0.13.2 matplotlib==3.10.0 numpy==2.0.2 pandas==2.2.2 -q

These packages are used for deep learning (TensorFlow), machine learning (scikit-learn), computer vision (OpenCV), data visualization (Seaborn, Matplotlib), numerical operations (NumPy), and data analysis (Pandas).

Step 2: Import all the important Classes from the installed packages:

import os

import random

import numpy as np

import pandas as pd

import seaborn as sns

import matplotlib.image as mpimg

import matplotlib.pyplot as plt

import math

import cv2

# Tensorflow modules

import keras

import tensorflow as tf

from tensorflow.keras.preprocessing.image import ImageDataGenerator

from tensorflow.keras.models import Sequential

from tensorflow.keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPooling2D,BatchNormalization

from tensorflow.keras.optimizers import Adam,SGD

from sklearn import preprocessing

from sklearn.model_selection import train_test_split

from sklearn.metrics import confusion_matrix

from tensorflow.keras.models import Model

from keras.applications.vgg16 import VGG16

# Display images using OpenCV

from google.colab.patches import cv2_imshow

#Imports functions for evaluating the performance of machine learning models

from sklearn.metrics import confusion_matrix, f1_score,accuracy_score, recall_score, precision_score, classification_report

from sklearn.metrics import mean_squared_error as mse

# Ignore warnings

import warnings

warnings.filterwarnings('ignore')

These packages are used for operating system interaction, numerical computing, data manipulation and visualization, computer vision, and building, training, and evaluating deep learning models using TensorFlow/Keras and scikit-learn.

# Set the seed using keras.utils.set_random_seed. This will set:

# 1) `numpy` seed

# 2) backend random seed

# 3) `python` random seed

tf.keras.utils.set_random_seed(812)

We set the random seed to tf.keras.utils.set_random_seed(812) to ensure reproducibility of our experiments. This function sets seeds for NumPy, the TensorFlow backend, and Python's random module, meaning that if you run the code again with the same seed, you'll get the same "random" results, making the model training and evaluation consistent. The number 812 itself is an arbitrary choice; any integer could be used as a seed.