train.py

# -*- coding: utf-8 -*-
"""train.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/drive/1m_MwpBggmETJ3cK3kfpG0Hj2t-eIYKqx
"""

import cv2
import os
import numpy as np
import numpy as np
from sklearn.model_selection import train_test_split
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense

#Preprocessing Function
def preprocess_image(img_path, target_size=(32, 32)):
    img = cv2.imread(img_path)
    img_resized = cv2.resize(img, target_size)
    return img_resized
#This is Google Collab Formatting
image_dir_positive = "/content/Positive"
image_dir_negative = "/content/Negative"
output_dir = "/content/Preprocessed"

preprocessed_images = []
labels = []

#Importing Positive Files
for filename in os.listdir(image_dir_positive):
    if filename.endswith(".jpg"):
        img_path = os.path.join(image_dir_positive, filename)
        preprocessed_img = preprocess_image(img_path)
        preprocessed_images.append(preprocessed_img)
        label = 1 #Positive Label
        labels.append(int(label))

        output_path = os.path.join(output_dir, filename)
        cv2.imwrite(output_path, preprocessed_img)
#Importing Negative Files
for filename in os.listdir(image_dir_negative):
    if filename.endswith(".jpg"):
        img_path = os.path.join(image_dir_negative, filename)
        preprocessed_img = preprocess_image(img_path)
        preprocessed_images.append(preprocessed_img)
        label = 0 #Negative Label
        labels.append(int(label))

        output_path = os.path.join(output_dir, filename)
        cv2.imwrite(output_path, preprocessed_img)

# Convert the list of images and labels to NumPy arrays
dataset = np.array(preprocessed_images)
labels = np.array(labels)

np.savez("/content/preprocess.npz", dataset=dataset, labels=labels)

X_train, X_test, y_train, y_test = train_test_split(dataset, labels, test_size=0.2, random_state=42)

#Very Simplistic CNN model
model = Sequential([
    Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)),
    MaxPooling2D((2, 2)),
    Conv2D(64, (3, 3), activation='relu'),
    MaxPooling2D((2, 2)),
    Flatten(),
    Dense(64, activation='relu'),
    Dense(1, activation='sigmoid')
])

#Compile the model
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

#Train the model
model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))

#Evaluate the model
loss, accuracy = model.evaluate(X_test, y_test)
print("Test Loss:", loss)
print("Test Accuracy:", accuracy)

#Save the model
model.save("Homework4_ImageModel.h5")