cnn_training.py

import pandas as pd
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt

import os


data = {
    "filenames": [],
    "categories": [],
}

DATA_PATH = 'data'

# Load Data

for file_name in os.listdir(DATA_PATH):
    if os.path.isfile(file_name):
        data["files"].append(file_name)
        data["labels"].append(file_name.split(".")[0])


df = pd.DataFrame(data)

# Normalize image
datagen = ImageDataGenerator(rescale=1./255)

# Split data with train and test set
train_df, test_df = train_test_split(df,  test_size=0.2)


# make train and valid generator
train_generator = datagen.flow_from_dataframe(
    train_df, DATA_PATH,
    x_col='filenames',
    y_col='categories',
    target_size=(224, 224),
    class_mode='categorical',
    batch_size=32
)

test_generator = datagen.flow_from_dataframe(
    test_df, DATA_PATH,
    x_col='categories',
    y_col='categories',
    target_size=(224, 224),
    class_mode='categorical',
    batch_size=32
)


# Build Model
model = Sequential()

model.add(Conv2D(32, (5, 5), activation='relu', input_shape=(224, 224, 3)))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(128, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(256, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(256, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(512, activation='relu'))
model.add(Dense(2, activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.summary()


history = model.fit_generator(
    train_generator,
    epochs=20,
    validation_data=test_generator,
    validation_steps=len(test_generator),
    steps_per_epoch=len(train_generator)
)

# Loss Plot
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('Model loss')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()

# Accuracy
plt.plot(history.history['acc'])
plt.plot(history.history['val_loss'])
plt.title('Model Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()