mnist 3layers

둘째날수업.ipynb 실습

 

3개의 히든레이어를 가지는 MLP(MNIST 분류기) - Tensorflow

 

첫번째 레이어 : 256 유닛

 

두번째 레이어 : 256 유닛

 

세번째 레이어 : 256 유닛

 

배치사이즈 128

 

반복횟수 : 500

 

#import tensorflow as tf

import tensorflow.compat.v1 as tf

tf.compat.v1.disable_eager_execution()

from tensorflow import keras

#데이터 준비

(x_train, y_train), (x_test, y_test) = tf.keras.datasets.mnist.load_data()

 

x_train = x_train.reshape( -1, 28*28)

x_test = x_test.reshape(-1, 28*28)

 

y_train = keras.utils.to_categorical(y_train)

y_test = keras.utils.to_categorical(y_test)

 

print( y_train.shape)

 

# 모델 만들기

X = tf.placeholder(tf.float32, shape=[None, 784])

Y = tf.placeholder(tf.float32, shape=[None, 10])

 

W1 = tf.Variable(tf.random_normal(shape=[784, 256]))

B1 = tf.Variable(tf.random_normal(shape=[256]))

 

H1 = tf.matmul(X, W1) + B1

H1 = tf.nn.relu(H1)

W2 = tf.Variable(tf.random_normal(shape=[256,256]))

B2 = tf.Variable(tf.random_normal(shape=[256]))

 

H2 = tf.matmul(H1,W2) + B2

W3 = tf.Variable(tf.random_normal(shape=[256,256]))

B3 = tf.Variable(tf.random_normal(shape=[256]))

 

H3 = tf.matmul(H2, W3) + B3

WW = tf.Variable(tf.random_normal(shape=[256,10]))

BB = tf.Variable(tf.random_normal(shape=[10]))

logit = tf.matmul(H3, WW) + BB

pred = tf.nn.softmax(logit) ##model

 

loss = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logit, labels=Y)

loss = tf.reduce_mean(loss)

 

optimizer = tf.train.AdamOptimizer(learning_rate=0.01).minimize(loss) ## train

 

acc = tf.equal(tf.argmax(pred,axis=1), tf.argmax(Y,axis=1))

acc = tf.reduce_mean(tf.cast(acc, tf.float32))

 

#print(tf.argmax(pred,axis=1))

##모델 학습 -세션

 

sess = tf.Session()

sess.run(tf.global_variables_initializer())

 

epochs = 500

batch = 128

n_batch = len(x_train) // batch

 

for e in range(epochs):

for b in range(n_batch):

x= x_train[b*batch : (b+1)*batch]

y= y_train[b*batch : (b+1)*batch]

sess.run(optimizer, feed_dict = {X:x, Y:y})

 

print(sess.run(acc, feed_dict={X:x_train, Y:y_train}))

 

#모델 평가

accuracy = sess.run(acc, feed_dict={X:x_test, Y:y_test})

print("{0: .2f}%".format(accuracy * 100))

Deep Learning Day4.ipynb 실습

 

3개의 히든레이어를 가지는 MLP(MNIST 분류기) - keras

 

첫번째 레이어 : 256 유닛

 

두번째 레이어 : 256 유닛

 

세번째 레이어 : 256 유닛

 

배치사이즈 128

 

반복횟수 : 500

import tensorflow.compat.v1 as tf

tf.compat.v1.disable_eager_execution()

 

from tensorflow import keras

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

 

x_train = x_train.reshape(-1, 28*28)/255

x_test = x_test.reshape(-1, 28*28)/255

 

y_train = keras.utils.to_categorical(y_train)

y_test = keras.utils.to_categorical(y_test)

 

#모델만들기

model = keras.models.Sequential()

 

model.add(keras.layers.Dense(256,activation='relu'))

model.add(keras.layers.Dense(256,activation='relu'))

model.add(keras.layers.Dense(256,activation='relu'))

model.add(keras.layers.Dense(10,activation='softmax'))

#학습

model.compile(loss= keras.losses.categorical_crossentropy,

optimizer= keras.optimizers.Adam(learning_rate=0.01),

metrics = [keras.metrics.categorical_accuracy]

)

model.fit(x_train, y_train, batch_size=128, epochs=10, verbose=1)

model.summary()

acc=model.evaluate(x_test,y_test)

print(acc)

3개의 히든레이어를 가지는 MLP(CIFAR10 분류기) - keras

 

첫번째 레이어 : 256 유닛

 

두번째 레이어 : 256 유닛

 

세번째 레이어 : 256 유닛

 

배치사이즈 128

 

반복횟수 : 500

 

(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()

print(x_train.shape)

x_train = x_train.reshape(-1,32*32*3)/255

x_test = x_test.reshape(-1,32*32*3)/255

 

y_train = keras.utils.to_categorical(y_train)

y_test = kerras.utils.to_categorical(y_test)

 

medel= keras.models.Sequential()

medel.add(keras.layers.Dense(255,activation='relu'))

medel.add(keras.layers.Dense(255,activation='relu'))

medel.add(keras.layers.Dense(255,activation='relu'))

medel.add(keras.layers.Dense(10,activation='softmax'))

 

model.compile(loss= keras.losses.categorical_crossentropy,

optimizer= keras.optimizers.Adam(learning_rate=0.01),

metrics = [keras.metrics.categorical_accuracy]

)

model.fit(x_train, y_train, batch_size=128,epochs=10,verbose=1)

 

acc = model.evaluate(x_test,y_test)

model.summary()

print(acc)

 

 

7개의 레이어를 가지는 CNN(MNIST 분류기) - keras

#import tensorflow as tf

import tensorflow.compat.v1 as tf

tf.compat.v1.disable_eager_execution()

 

from tensorflow import keras

 

#데이터준비

(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

 

print(x_train.shape)

x_train = x_train.reshape(-1, 28,28,1) /255

x_test = x_test.reshape(-1,28,28,1)/255

 

y_train = keras.utils.to_categorical(y_train)

y_test = keras.utils.to_categorical(y_test)

#모델만들기

model = keras.models.Sequential()

 

model.add(keras.layers.Conv2D(16,(3,3),strides=(1,1), activation="relu", padding="same",input_shape=(28,28,1)))

model.add(keras.layers.MaxPooling2D(pool_size=(2,2)))

#model.add(keras.layers.Activation(keras.activations.relu))

 

model.add(keras.layers.Conv2D(32,(3,3),strides=(1,1),padding="same",activation="relu"))

model.add(keras.layers.MaxPooling2D(pool_size=(2,2)))

 

model.add(keras.layers.Flatten())

model.add(keras.layers.Dense(500))

model.add(keras.layers.Dense(10, activation='softmax'))

#model.add(keras.layers.Activation(keras.activations.softmax))

#모델 compile

model.compile(optimizer=keras.optimizers.Adam(learning_rate=0.01),

loss= keras.losses.categorical_crossentropy,

metrics=[keras.metrics.categorical_accuracy])

 

 

model.fit(x_train,y_train,batch_size=128, epochs=10, verbose=1)

 

acc= model.evaluate(x_test,y_test)

model.summary()

 

print(acc)