AI_파이썬_시각지능_CNN_Image_SmallData2024

Image Data Augmentation

---

Keras Update

---

!pip install keras-nightly

Collecting keras-nightly
  Downloading keras_nightly-3.6.0.dev2024101603-py3-none-any.whl.metadata (5.8 kB)
Requirement already satisfied: absl-py in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (1.4.0)
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (1.26.4)
Requirement already satisfied: rich in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (13.9.2)
Requirement already satisfied: namex in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (0.0.8)
Requirement already satisfied: h5py in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (3.11.0)
Requirement already satisfied: optree in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (0.13.0)
Requirement already satisfied: ml-dtypes in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (0.4.1)
Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from keras-nightly) (24.1)
Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from optree->keras-nightly) (4.12.2)
Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich->keras-nightly) (3.0.0)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich->keras-nightly) (2.18.0)
Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich->keras-nightly) (0.1.2)
Downloading keras_nightly-3.6.0.dev2024101603-py3-none-any.whl (1.2 MB)
   ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 18.2 MB/s eta 0:00:00
Installing collected packages: keras-nightly
Successfully installed keras-nightly-3.6.0.dev2024101603

---

데이터가 부족한 세상으로 떠나기 위한 준비

---

import keras

---

# from keras.preprocessing.image import load_img
# from keras.preprocessing.image import img_to_array

from keras.utils import load_img, img_to_array

import numpy as np
import matplotlib.pyplot as plt

---

!wget -O Batman.webp https://github.com/DrKAI/image/raw/main/.webp
# !wget -O Batman.jpg https://ichef.bbci.co.uk/news/640/cpsprodpb/C120/production/_104304494_mediaitem104304493.jpg

--2024-10-23 05:40:59--  https://github.com/DrKAI/image/raw/main/Batman01.webp
Resolving github.com (github.com)... 140.82.114.3
Connecting to github.com (github.com)|140.82.114.3|:443... connected.
HTTP request sent, awaiting response... 302 Found
Location: https://raw.githubusercontent.com/DrKAI/image/main/Batman01.webp [following]
--2024-10-23 05:40:59--  https://raw.githubusercontent.com/DrKAI/image/main/Batman01.webp
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 281262 (275K) [image/webp]
Saving to: ‘Batman.webp’

Batman.webp         100%[===================>] 274.67K  --.-KB/s    in 0.03s   

2024-10-23 05:40:59 (10.6 MB/s) - ‘Batman.webp’ saved [281262/281262]

---

image_org = load_img(".webp")
image = img_to_array(image_org)
image.shape  # height, width, channel

(1600, 1136, 3)

---

plt.figure(figsize=(12,8))
plt.imshow(image/255)
plt.show()

---

image = np.expand_dims(image, axis=0) # 데이터 개수를 담당할 차원 추가

---

image.shape

(1, 1600, 1136, 3)

---

Image Augmentation Layers

• 케라스 공식 문서 참고

---

import keras

---

aug_layers = [keras.layers.RandomRotation(factor=(-0.3,0.3)),
              keras.layers.RandomTranslation(height_factor=(-0.3,0.3), width_factor=(-0.3,0.3)),
              keras.layers.RandomZoom(height_factor=(-0.2,0.2), width_factor=(-0.2,0.2)),
              keras.layers.RandomFlip(mode='horizontal_and_vertical')
              ]

---

aug_layers

[<RandomRotation name=random_rotation, built=False>,
 <RandomTranslation name=random_translation, built=False>,
 <RandomZoom name=random_zoom, built=False>,
 <RandomFlip name=random_flip, built=False>]

---

def image_augmentation(images) :
    for layer in aug_layers :
        images = layer(images)
        # print(images)
    return images

---

print(image_augmentation(image).shape)

(1, 1600, 1136, 3)

---

for i in range(4) :
    aug_imgs = image_augmentation(image)
    # temp = keras.preprocessing.image.array_to_img(aug_imgs)

    plt.imshow( aug_imgs[0]/255 )
    plt.axis('off')
    plt.show()

---