CNN AI's main file: blog(https://jimut123.github.io/blogs/cnn_games_ai.html)

cnn_ai.py

import keras
from keras.models import load_model
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv2D, MaxPooling2D
from sklearn.model_selection import train_test_split
import numpy as np
from sklearn import preprocessing
import cv2

X = []
Y = []

with open ('actions.csv', 'r') as f:
    for line in f:
        Y.append(line.rstrip())


all_images = []
img_num = 0
while img_num < 3000: #3000 denotes the total no of input images
        img = cv2.imread('images/frame_{0}.jpg'.format(img_num), cv2.IMREAD_GRAYSCALE)
        img = img[:, :, np.newaxis]
        all_images.append(img)
        img_num += 1

X = np.array(all_images)


# split into test and train set
x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=.2, random_state=5)

# convert class vectors to binary class matricies for use in catagorical_crossentropy loss below
# number of action classifications
classifications = 3
y_train = keras.utils.to_categorical(y_train, classifications)
y_test = keras.utils.to_categorical(y_test, classifications)

#reference:-https://github.com/keras-team/keras/blob/master/examples/cifar10_cnn.py
# CNN model
model = Sequential()
model.add(Conv2D(32, (3, 3), padding='same',
                 input_shape=x_train.shape[1:]))
model.add(Activation('relu'))
model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Conv2D(64, (3, 3), padding='same'))
model.add(Activation('relu'))
model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))

model.add(Flatten())
model.add(Dense(512))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(3))
model.add(Activation('softmax'))

# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

model.fit(x_train, y_train,
              batch_size=32,
              epochs=30,
              validation_data=(x_test, y_test),
              shuffle=True)
#save weights post training
model.save('pong.h5')