115 lines
3.6 KiB
Python
115 lines
3.6 KiB
Python
|
|
import os
|
|
import numpy as np
|
|
import random
|
|
import shutil
|
|
from keras.models import Sequential
|
|
from keras.layers import Conv2D, Flatten, MaxPooling2D, Dense
|
|
from keras.preprocessing import image
|
|
|
|
#dataset from https://www.kaggle.com/asdasdasasdas/garbage-classification
|
|
|
|
'''#sepperating the file into training and testing data, creation of folders by hand removal of 75 images from papers for a more even distribution
|
|
def sepperate(type):
|
|
for i in type:
|
|
folder = "Garbage classification\\Garbage classification\\" + i
|
|
destination = "Garbage classification\\testset\\" + i
|
|
howmany = len(os.listdir(folder))
|
|
for j in range(int(howmany*0.2)):
|
|
move1 = random.choice(os.listdir(folder))
|
|
source = "Garbage classification\\Garbage classification\\" + i + "\\" + move1
|
|
d = shutil.move(source, destination, copy_function = shutil.copytree)
|
|
|
|
|
|
types = ["cardboard", "glass", "metal", "paper", "plastic"]
|
|
sepperate(types)
|
|
os.rename("Garbage classification\\Garbage classification", "Garbage classification\\trainset")
|
|
'''
|
|
|
|
|
|
classifier = Sequential()
|
|
classifier.add(Conv2D(32, (3, 3), input_shape=(110, 110, 3), activation = "relu"))
|
|
classifier.add(MaxPooling2D(pool_size = (2, 2)))
|
|
classifier.add(Conv2D(64, (3, 3), activation = "relu"))
|
|
classifier.add(MaxPooling2D(pool_size=(2, 2)))
|
|
# this layer in ver 4
|
|
classifier.add(Conv2D(32, (3, 3), activation = "relu"))
|
|
classifier.add(MaxPooling2D(pool_size=(2, 2)))
|
|
# -----------------
|
|
classifier.add(Flatten())
|
|
classifier.add(Dense(activation = "relu", units = 64 ))
|
|
classifier.add(Dense(activation = "softmax", units = 5))
|
|
classifier.compile(optimizer = "adam", loss = "binary_crossentropy", metrics = ["accuracy"])
|
|
|
|
|
|
from keras.preprocessing.image import ImageDataGenerator
|
|
|
|
train_datagen = ImageDataGenerator(
|
|
rescale=1./255,
|
|
shear_range=0.1,
|
|
zoom_range=0.1,
|
|
width_shift_range=0.1,
|
|
height_shift_range=0.1,
|
|
horizontal_flip=True,
|
|
vertical_flip=True,
|
|
)
|
|
|
|
test_datagen = ImageDataGenerator(
|
|
rescale=1./255,
|
|
validation_split=0.1
|
|
)
|
|
|
|
train_generator = train_datagen.flow_from_directory(
|
|
"Garbage classification\\trainset",
|
|
target_size=(110, 110),
|
|
batch_size=16,
|
|
class_mode='categorical',
|
|
#seed=0
|
|
)
|
|
|
|
test_generator = test_datagen.flow_from_directory(
|
|
"Garbage classification\\testset",
|
|
target_size=(110, 110),
|
|
batch_size=16,
|
|
class_mode='categorical',
|
|
)
|
|
|
|
|
|
#Teaching the classifier
|
|
'''classifier.fit_generator( train_generator, steps_per_epoch = 150, epochs = 25, validation_data = test_generator )
|
|
classifier.save_weights('model_ver_4.h5')'''
|
|
|
|
import matplotlib.pyplot as plt
|
|
labels = (train_generator.class_indices)
|
|
labels = dict((value,key) for key,value in labels.items())
|
|
|
|
|
|
classifier.load_weights("model_ver_4.h5")
|
|
import random
|
|
|
|
|
|
def getTrashPhoto(x, type):
|
|
for i in range(x):
|
|
kind = random.choice(type)
|
|
path = "Garbage classification\\testset\\" + kind
|
|
file = random.choice(os.listdir(path))
|
|
path = "Garbage classification\\testset\\" + kind + "\\" + file
|
|
gz = image.load_img(path, target_size = (110,110))
|
|
ti = image.img_to_array(gz)
|
|
ti=np.array(ti)/255.0
|
|
ti = np.expand_dims(ti, axis = 0)
|
|
prediction = classifier.predict(ti)
|
|
plt.subplot(1, 3, i+1)
|
|
plt.imshow(gz)
|
|
plt.title("AI thinks:%s \nReality:\n %s" % (labels[np.argmax(prediction)], file))
|
|
plt.show()
|
|
|
|
|
|
types = ["cardboard", "glass", "metal", "paper", "plastic"]
|
|
type = ["metal"]
|
|
|
|
getTrashPhoto(3, types)
|
|
|
|
|
|
plt.show()
|