class MNISTServer: def __init__(self): self.lenet = LeNet() def predict(self, image): preprocessed_image = np.array(image, dtype='float32') pmf = self.lenet.predict(preprocessed_image) return [Prediction(digit=digit, probability=probability) for digit, probability in pmf]
class MNISTServer:
def __init__(self):
self.lenet = LeNet()
def predict(self, image):
preprocessed_image = np.array(image, dtype='float32')
pmf = self.lenet.predict(preprocessed_image)
return [
Prediction(digit=digit, probability=probability)
for digit, probability in pmf
]
def aiTest(images, shape):
model = LeNet()
y_test = []
x_test = images
generate_images = []
for image in x_test:
confidence = model.predict(image)[0]
predicted_class = np.argmax(confidence)
y_test.append(predicted_class)
attacker = PixelAttacker((x_test, y_test))
for i in range(len(x_test)):
generate_images.append(attacker.attack(i, model, verbose=False)[10])
return generate_images
import os
import cv2
import numpy as np
from lenet import LeNet
data_dir = "mnist/test"
net = LeNet()
net.load("lenet.npy")
files = os.listdir(data_dir)
images = []
labels = []
for f in files:
img = cv2.imread(os.path.join(data_dir, f), cv2.IMREAD_GRAYSCALE)
img = cv2.resize(img, (32, 32))
img = img.astype(np.float32).reshape(32, 32, 1) / 255.0
images.append(img)
labels.append(int(f[0]))
x = np.array(images)
y = np.array(labels)
predict = net.predict(x)
tp = np.sum(predict == y)
accuracy = float(tp) / len(files)
print("accuracy=%f" % accuracy)
