수수께끼 고양이

6x6x2 입력 import numpy as np np.random.seed(1) image=np.random.randint(5, size=(4,4,2)) print('image_0=\n', image[:,:,0]) print('image_1=\n', image[:,:,1]) filter=np.random.randint(5, size=(3,3,2)) print('filter_0=\n', filter[:,:,0]) print('filter_1=\n', filter[:,:,1]) image_pad=np.pad(image,((1,1),(1,1),(0,0))) print('image_pad_0=\n', image_pad[:,:,0]) print('image_pad_1=\n', image_pad[:,:,1]) c..

3x3x2 입력 이미지 import numpy as np np.random.seed(1) image=np.random.randint(5, size=(3,3,2)) print('image_0=\n', image[:,:,0]) print('image_1=\n', image[:,:,1]) filter=np.random.randint(5, size=(3,3,2)) print('filter_0=\n', filter[:,:,0]) print('filter_1=\n', filter[:,:,1]) image_x_filter=image*filter print('image_x_filter_0=\n', image_x_filter[:,:,0]) print('image_x_filter_1=\n', image_x_filter[:..

1. 1~9 사이의 정수값으로 구성된 3x3 랜덤 필터를 만들어 적용해보시오 import numpy as np import cv2 import matplotlib.pyplot as plt image_color=cv2.imread('../images/cat.jpg') print('image_color.shape =',image_color.shape) image=cv2.cvtColor(image_color,cv2.COLOR_BGR2GRAY) print('image.shape =',image.shape) np.random.seed(1) filter=np.random.randint(1,10, size=(3,3,3))/9 image_pad=np.pad(image,((1,1),(1,1))) print('image_..

선명한 이미지 추출하기 import numpy as np import cv2 import matplotlib.pyplot as plt image_color=cv2.imread('../images/cat.jpg') print('image_color.shape =',image_color.shape) image=cv2.cvtColor(image_color,cv2.COLOR_BGR2GRAY) print('image.shape =',image.shape) filter=np.array([ [-1,-1,-1], [-1,9,-1], [-1,-1,-1] ]) image_pad=np.pad(image,((5,5),(5,5))) print('image_pad.shape =', image_pad.shape) convoluti..

import numpy as np import cv2 import matplotlib.pyplot as plt image_bgr=cv2.imread('../images/cat.jpg') image=cv2.cvtColor(image_bgr,cv2.COLOR_BGR2RGB) print('image.shape =',image.shape) filter=np.array([[ [1,1,1], [1,1,1], [1,1,1] ],[ [1,1,1], [1,1,1], [1,1,1] ],[ [1,1,1], [1,1,1], [1,1,1] ]])/9 image_pad=np.pad(image,((1,1),(1,1),(0,0))) print('image_pad.shape =', image_pad.shape) convolution=..

1. import numpy as np import cv2 import matplotlib.pyplot as plt image_color=cv2.imread('../images/cat.jpg') print('image_color.shape =',image_color.shape) image=cv2.cvtColor(image_color,cv2.COLOR_BGR2GRAY) print('image.shape =',image.shape) filter=np.array([ [1,1,1], [1,1,1], [1,1,1] ])/9 image_pad=np.pad(image,((1,1),(1,1))) print('image_pad.shape =', image_pad.shape) convolution=np.zeros_like..

import numpy as np np.random.seed(1) H,W,C=56,156,48 F=128 image=np.random.randint(5,size=(H,W,C)) print(image.shape) filter=np.random.randint(5,size=(F,3,3,C)) print('filter_0=\n', filter[0]) print('filter_0=\n', filter[1]) image_pad=np.pad(image,((1,1),(1,1),(0,0))) print('image_pad=\n', image_pad) convolution=np.zeros((H,W,F)) for fn in range(F): for row in range(H): for col in range(W): wind..

3x3 입력 : filter size import numpy as np np.random.seed(1) image=np.random.randint(5, size=(3,3)) print('image=\n', image) filter=np.random.randint(5, size=(3,3)) print('filter=\n',filter) image_x_filter=image*filter print('image_x_filter=\n',image_x_filter) convolution =np.sum(image_x_filter) print('convolution=\n',convolution) 4x4 입력 : stride import numpy as np np.random.seed(1) image=np.random..

임의 흑백 이미지 데이터 셋 생성하기 import tensorflow as tf import numpy as np X=np.random.randint(0,256,(60000,28,28)) YT=np.random.randint(0,10,(60000,)) x=np.random.randint(0,256,(10000,28,28)) yt=np.random.randint(0,10,(10000,)) print(X.shape, YT.shape, x.shape, yt.shape) import matplotlib.pyplot as plt plt.imshow(X[0]) plt.show() print(YT[0]) 임의 흑백 이미지 데이터 셋 학습하기 import tensorflow as tf import numpy as np..

CIFAR-10 데이터 셋은 6만장, 10 종류의 32x32 컬러 이미지로 구성되며,각각의 종류는 6천장의 이미지로 되어 있습니다. 6만장의 이미지는 5만장의 훈련용 이미지와 1만장의 시험용 이미지로 구성됩니다. import tensorflow as tf mnist=tf.keras.datasets.cifar10 (X,YT),(x,yt)=mnist.load_data() print(X.shape, YT.shape, x.shape, yt.shape) import matplotlib.pyplot as plt plt.imshow(X[0]) plt.show() print(YT[0]) CIFAR-10 데이터 셋 학습하기 import tensorflow as tf mnist=tf.keras.datasets.cifar1..