[Tensorflow] 분류(Classification) 신경망 실습

본 실습은 크게 3가지 데이터 셋을 활용했습니다.

1. Iris Dataset

2. MNIST

3. MNIST Fashion

 

Iris Classification

1. Load dataset

from sklearn.datasets import load_iris
iris = load_iris()
X = iris.data
y = iris.target

2. OnehotEncoding

# One hot encoding
from sklearn.preprocessing import OneHotEncoder
enc = OneHotEncoder(sparse=False, handle_unknown='ignore')
enc.fit(y.reshape(len(y), 1))
y_onehot = enc.transform(y.reshape(len(y), 1))

3. Train / Test Split

from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y_onehot,
                                                   test_size=0.2,
                                                   random_state=13)

4. Model Design

model = tf.keras.Sequential([
    tf.keras.layers.Dense(32, activation='relu', input_shape=(4,)),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(32, activation='relu'),
    tf.keras.layers.Dense(3, activation='softmax')
])

model.summary()

5. Compile & Fit

# Compile - adma, cc, acc
model.compile(optimizer='adam', loss='categorical_crossentropy',
             metrics=['accuracy'])

# fit - hist, epochs=100
hist = model.fit(X_train, y_train, epochs=100)

6. Evaluate and Visualize

# Evaluate
model.evaluate(X_test, y_test, verbose=2)

# Vis
import matplotlib.pyplot as plt
%matplotlib inline

plt.plot(hist.history['loss'])
plt.plot(hist.history['accuracy'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epochs')
plt.show()

 

MNIST Classification

1. Load data and split

# Load
import tensorflow as tf
mnist = tf.keras.datasets.mnist

# Split and scaling
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

2. Modeling and compile

# Design - 3 layers
model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28,28)),
    tf.keras.layers.Dense(1000, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

# Compile - adma, scc, acc
model.compile(optimizer='adam',
             loss='sparse_categorical_crossentropy',
             metrics=['accuracy'])

4. Model Fitting

import time
start_time = time.time()
hist = model.fit(x_train, y_train, validation_data=(x_test, y_test),
                epochs=10, batch_size=100, verbose=1)
print('Fit time: ', time.time() - start_time)

5. Evaluate and Visualize

# Evaluate
score = model.evaluate(x_test, y_test)
print('Test Loss: ', score[0])
print('Test Accuracy: ', score[1])

# Vis
import matplotlib.pyplot as plt
%matplotlib inline
plot_target = ['loss', 'val_loss', 'accuracy', 'val_accuracy']
plt.figure(figsize=(12, 8))

for each in plot_target:
    plt.plot(hist.history[each], label=each)
    
plt.legend()
plt.grid()
plt.show()

6. Wrong data Visualize

import numpy as np
predicted_result = model.predict(x_test)
predicted_labels = np.argmax(predicted_result, axis=1)

wrong_result = []
for n in range(0, len(y_test)):
    if predicted_labels[n] != y_test[n]:
        wrong_result.append(n)

import random
samples = random.choices(population=wrong_result, k=16)

plt.figure(figsize=(14, 12))

for idx, n in enumerate(samples):
    plt.subplot(4, 4, idx+1)
    plt.imshow(x_test[n].reshape(28,28), cmap='Greys', interpolation='nearest')
    plt.title('Label: ' + str(y_test[n]) + ' / Predict: ' + str(predicted_labels[n]))
    plt.axis('off')
plt.show()

 

MNIST FASION Classification

1. Load data and split

# Load
import tensorflow as tf
fashion_mnist = tf.keras.datasets.fashion_mnist

# Split and scaling
(X_train, y_train), (X_test, y_test) = fashion_mnist.load_data()
X_train, X_test = X_train / 255.0, X_test / 255.0

2. Check data

import random
import matplotlib.pyplot as plt
%matplotlib inline

samples = random.choices(population=range(0, len(y_train)), k=16)
plt.figure(figsize=(14,12))
for idx, n in enumerate(samples):
    plt.subplot(4, 4, idx+1)
    plt.imshow(X_train[n].reshape(28, 28), cmap='Greys', interpolation='nearest')
    plt.title('Label : ' + str(y_train[n]))
    plt.axis('off')
plt.show()

3. Modeling and compile

model = tf.keras.models.Sequential([
    tf.keras.layers.Flatten(input_shape=(28, 28)),
    tf.keras.layers.Dense(1000, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

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

4. Model Fitting

import time
start_time = time.time()
hist = model.fit(X_train, y_train, validation_data=(X_test, y_test),
                epochs=10, batch_size=100, verbose=1)
print('Fit time : ', time.time() - start_time)

5. Evaluate and Visualize

# Evaluate
score = model.evaluate(X_test, y_test)
print('Test Loss : ', score[0])
print('Test Accuracy : ', score[1])

# Vis
import matplotlib.pyplot as plt
%matplotlib inline

plot_target = ['loss', 'val_loss', 'accuracy', 'val_accuracy']
plt.figure(figsize=(12, 8))

for each in plot_target:
    plt.plot(hist.history[each], label=each)
    
plt.legend()
plt.grid()
plt.show()