실습

• Fashion_mnist 데이터를 기반으로 분류 학습을 수행 해라

데이터 로드

'''
라이브러리들을 불러오자.
'''
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

import random as rd
from sklearn.metrics import accuracy_score

import tensorflow as tf
from tensorflow import keras

(train_x, train_y), (test_x, test_y) = keras.datasets.fashion_mnist.load_data()

Scaling

max_n , min_n = train_x.max() , train_x.min()
train_x = (train_x - max_n) / (max_n - min_n)
test_x = (test_x - max_n) / (max_n - min_n)

reshape

train_x = train_x.reshape(train_x.shape[0] ,h,w,1)
test_x = test_x.reshape(test_x.shape[0],h,w,1)
print(train_x.shape , train_y.shape , test_x.shape , test_y.shape)

one-hot-encoding

from tensorflow.keras.utils import to_categorical

class_n = len(np.unique(train_y))
class_n

train_y = to_categorical(train_y , class_n)
test_y = to_categorical(test_y , class_n)

model

from tensorflow.keras.backend import clear_session
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Dense, Flatten, Conv2D, MaxPool2D

from tensorflow.keras.callbacks import EarlyStopping


from keras.src.engine.training import optimizer
clear_session()

il = Input(shape =(28,28,1))
hl = Conv2D(
    filters = 32,
    kernel_size = (3,3),
    strides=  (1,1),
    padding = 'same',
    activation = 'relu'
)(il)
hl = keras.layers.BatchNormalization()(hl)
hl = Conv2D(
    filters = 32,
    kernel_size = (3,3),
    strides=  (1,1),
    padding = 'same',
    activation = 'relu'
)(hl)
hl = keras.layers.BatchNormalization()(hl)
hl = MaxPool2D(pool_size = (2,2),strides = (2,2))(hl)
hl = keras.layers.Dropout(0.25)(hl)
hl = Conv2D(filters = 64,
            kernel_size = (3,3),
            strides=  (1,1),
            padding = 'same',
            activation = 'relu'
            )(hl)
hl = keras.layers.BatchNormalization()(hl)
hl = Conv2D(filters = 64,
            kernel_size = (3,3),
            strides= (1,1),
            padding = 'same',
            activation = 'relu')(hl)

hl = keras.layers.BatchNormalization()(hl)
hl = MaxPool2D(pool_size = (2,2) , strides=(3,3))(hl)
hl = keras.layers.Dropout(0.25)(hl)
hl = Flatten()(hl)
hl = Dense(512 , activation = 'relu')(hl)
hl = keras.layers.BatchNormalization()(hl)
ol = Dense(10 , activation = 'softmax')(hl)

model = Model(il , ol)

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

model setting

es = EarlyStopping(monitor = 'val_loss',
                   min_delta = 0,
                   patience = 3,
                   verbose = 1,
                   restore_best_weights = True)
                   
hist = model.fit(train_x , train_y , validation_split=0.2 , epochs = 10000 , verbose = 1 ,callbacks = [es])

시각화

plt.figure(figsize=(10, 5))
plt.plot(hist.history['accuracy'])
plt.plot(hist.history['val_accuracy'])
plt.title('Accuracy : Training vs Validation')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.legend(['Training', 'Validation'], loc=0)
plt.show()

plt.figure(figsize=(10, 5))
plt.plot(hist.history['loss'])
plt.plot(hist.history['val_loss'])
plt.title('Loss : Training vs Validation')
plt.ylabel('Loss')
plt.xlabel('Epoch')
plt.legend(['Training', 'Validation'], loc=0)
plt.show()