PhilipPurwoko

section .data
	pesanSiang:     db 'Selamat Siang',10
	pesanSiangLen:  equ $-pesanSiang
	
	pesanPagi:     db 'Selamat Pagi',10
	pesanPagiLen:  equ $-pesanPagi

section .text
	global _start

PhilipPurwoko

from tensorflow import keras
from sklearn.metrics import classification_report
import numpy as np

# Load data provided by keras
data = keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = data.load_data()

# Create model using sequential API
model = keras.Sequential([

PhilipPurwoko

package inheritance;
public class Dosen extends Pegawai {
    long gatun = 1000000;
    
    void hitungGatun(){
        System.out.print("Gaji Tunjangan : ");
        System.out.println(this.namaPegawai + " " + this.gatun);
    }
    
    void hitungGatot(){

PhilipPurwoko

import cv2
import datetime
import numpy as np
import matplotlib.pyplot as plt
import tensorflow as tf
keras = tf.keras

# Blit function to put text in video
def blit(text,frame,color,position=(100, 100)):
    cv2.putText(frame, text, position, cv2.FONT_HERSHEY_SIMPLEX, 2, color, 4, cv2.LINE_4)

PhilipPurwoko

def predict(unseen_image = []):
    test_data = batchData(unseen_image,for_test=True)
    prediction = model.predict(test_data)

    for image,pred in zip(unseen_image,prediction):
        fig,axes = plt.subplots(nrows=1,ncols=2)
        axes[0].imshow(processImage(image))
        axes[0].axis(False)
        axes[0].set_title('Actual Image')

PhilipPurwoko

# Create early stopping callback
early_stopping = keras.callbacks.EarlyStopping(monitor='val_loss',patience=3)

# Store model history into variable
history = model.fit(train_data,validation_data = valid_data,validation_freq=1,epochs = 50,callbacks = [early_stopping],verbose = 1,)

# Plot model training history
def plot_history():
    plt.plot(history.history['acc'],label='acc')
    plt.plot(history.history['val_acc'],label='val_acc')

PhilipPurwoko

# Create model structure
model = keras.Sequential([
    # Input Layer
    keras.layers.Conv2D(input_shape=(224,224,3),filters=32,kernel_size=(3,3),activation='relu'),
    keras.layers.MaxPooling2D(),
    
    # Hidden Layer
    keras.layers.Conv2D(input_shape=(224,224,3),filters=64,kernel_size=(3,3),activation='relu'),
    keras.layers.MaxPooling2D(),
    keras.layers.Conv2D(input_shape=(224,224,3),filters=128,kernel_size=(3,3),activation='relu'),

PhilipPurwoko

# Processing image files into numpy array
def process_label(label):
    label = [i == unique_label for i in label]
    label = np.array(label).astype(int)
    return label
  
def processImage(path):
    image = tf.io.read_file(path)
    image = tf.image.decode_jpeg(image,channels=3)
    image = tf.image.convert_image_dtype(image,tf.float32)

PhilipPurwoko

import os
import random
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
keras = tf.keras

PhilipPurwoko

import pickle

with open('AI_DrugClassifier.pkl','rb') as file:
    model = pickle.load(file)
    
def self_prediction():
    age = input('Age : ')
    sex = input('Sex : ')
    bp = input('BP : ')
    chol = input('Cholesterol : ')