opencv filter

import cv2
import numpy as np
from matplotlib import pyplot as plt

img = cv2.imread('opencv_logo.png')

kernel = np.ones((5,5),np.float32)/25
dst = cv2.filter2D(img,-1,kernel)

plt.subplot(121),plt.imshow(img),plt.title('Original')
plt.xticks([]), plt.yticks([])
plt.subplot(122),plt.imshow(dst),plt.title('Averaging')
plt.xticks([]), plt.yticks([])
plt.show()

Resources S3

dowload di sini

Contoh ReadData pada Google

from keras.models import Sequential

from keras.layers import Dense

import numpy

from scipy.spatial import Delaunay

import pandas as pd

def ReadData(sf):

sdir="drive/My Drive/Colab Notebooks"

sff="%s/%s"%(sdir ,sf)

print("Baca file :",sff)

df = array(pd.read_csv(sff,header=None))

df1 = pd.DataFrame(df)

return df1.values

def SaveData(sf,m):

sdir="drive/My Drive/Colab Notebooks"

sff="%s/%s"%(sdir ,sf)

print("Simpan File :",sff)

savetxt(sff, m, delimiter=',',newline='\r\n')

# load and prepare the dataset

#dataset = numpy.loadtxt("cb.csv", delimiter=",")

#X = dataset[:,0:8]

#Y = dataset[:,8]

X=numpy.array([[0,0],[0,1],[1,0],[1,1]]);

Y=numpy.array([[0],[1],[1],[0]]);

# 1. define the network

model = Sequential()

model.add(Dense(1000, input_dim=2, activation='sigmoid'))

model.add(Dense(1, activation='sigmoid'))

# 2. compile the network

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

# 3. fit the network

history = model.fit(X, Y, epochs=10000, batch_size=1)

#history = model.fit(X, Y, epochs=2000)

# 4. evaluate the network

loss, accuracy = model.evaluate(X, Y)

print("\nLoss: %.2f, Accuracy: %.2f%%" % (loss, accuracy*100))

# 5. make predictions

probabilities = model.predict(X)

predictions = [float(numpy.round(x)) for x in probabilities]

accuracy = numpy.mean(predictions == Y)

print("Prediction Accuracy: %.2f%%" % (accuracy*100))