naive_inception.py

# -*- coding: utf-8 -*-
"""
Created on Thu Mar 14 22:16:29 2019

@author: tanma
"""
import keras
import numpy as np
from keras.datasets import mnist
(X_train, y_train), (X_test, y_test) = mnist.load_data()

X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train = X_train / 255.0
X_test = X_test / 255.0

from keras.utils import np_utils
y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)

image_size = X_train.shape[1]


X_train = np.reshape(X_train,[-1, image_size, image_size, 1])
X_test = np.reshape(X_test,[-1, image_size, image_size, 1])
X_train = X_train.astype('float32') / 255
X_test = X_test.astype('float32') / 255

from keras.layers import Input
input_img = Input(shape = (28, 28, 1))

from keras.layers import Conv2D, MaxPooling2D
tower_1 = Conv2D(64, (1,1), padding='same', activation='relu')(input_img)
tower_1 = Conv2D(64, (3,3), padding='same', activation='relu')(tower_1)
tower_2 = Conv2D(64, (1,1), padding='same', activation='relu')(input_img)
tower_2 = Conv2D(64, (5,5), padding='same', activation='relu')(tower_2)
tower_3 = MaxPooling2D((3,3), strides=(1,1), padding='same')(input_img)
tower_3 = Conv2D(64, (1,1), padding='same', activation='relu')(tower_3)

output = keras.layers.concatenate([tower_1, tower_2, tower_3], axis = 3)

from keras.layers import Flatten, Dense
output = Flatten()(output)
out    = Dense(10, activation='softmax')(output)

from keras.models import Model
model = Model(inputs = input_img, outputs = out)

from keras.optimizers import SGD
epochs = 25
lrate = 0.01
decay = lrate/epochs
sgd = SGD(lr=lrate, momentum=0.9, decay=decay, nesterov=False)
model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
model.fit(X_train, y_train, validation_data=(X_test, y_test), epochs=epochs, batch_size=32)

from keras.models import model_from_json
import os
model_json = model.to_json()
with open("model.json", "w") as json_file:
    json_file.write(model_json)
model.save_weights(os.path.join(os.getcwd(), 'model.h5'))

scores = model.evaluate(X_test, y_test, verbose=0)
print("Accuracy: %.2f%%" % (scores[1]*100))