RyanKor

...
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(32, activation='relu'),
...

RyanKor

import tensorflow as tf
from tensorflow import keras

import matplotlib.pyplot as plt

import numpy as np

import os
import zipfile

RyanKor

history = model.fit(train_generator, epochs=25, steps_per_epoch=10, validation_data = validation_generator, verbose = 1, validation_steps=3)

RyanKor

history = model.fit(train_generator, epochs=25, steps_per_epoch=10, validation_data = validation_generator, verbose = 1, validation_steps=3)

    tf.keras.layers.Dense(512, activation='relu'),
    tf.keras.layers.Dense(7, activation='softmax')
])


model.summary()

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

RyanKor

model = tf.keras.models.Sequential([

    tf.keras.layers.Conv2D(64, (3,3), activation='relu', input_shape=(227, 227, 3)),
    tf.keras.layers.MaxPooling2D(2, 2),

    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

    tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D(2,2),

RyanKor

## CNN 다중 분류 이미지 sample test

import keras_preprocessing
from keras_preprocessing import image
from keras_preprocessing.image import ImageDataGenerator

training_datagen = ImageDataGenerator(
      rescale = 1./255,
	  rotation_range=40,
      width_shift_range=0.2,

RyanKor

## CNN 다중 분류 이미지 sample test

import keras_preprocessing
from keras_preprocessing import image
from keras_preprocessing.image import ImageDataGenerator

training_datagen = ImageDataGenerator(
      rescale = 1./255,
	  rotation_range=40,
      width_shift_range=0.2,

RyanKor

# validation image show
for i, img_path in enumerate(val_file[:16]):
    sp = plt.subplot(nrows, ncols, i + 1)
    sp.axis('Off')
    img = mpimg.imread(validation_dir + img_path)
    plt.imshow(img)

plt.show()

RyanKor

%matplotlib inline
import matplotlib.image as mpimg

# 이미지를 matplotlib를 사용해서 4 * 4 형태의 격자로 출력 예정
nrows = 4
ncols = 4

RyanKor

fig = plt.gcf()
fig.set_size_inches(ncols * 4, nrows * 4)

for folder_name in os.listdir(train_dir):
    for i, img_path in enumerate(train_file[folder_name][:4]):
        sp = plt.subplot(nrows, ncols, i + 1)
        sp.axis('Off')
        img = mpimg.imread(train_dir + folder_name + "/" + img_path)
        plt.imshow(img)