print("Input data shape", shape(data))
index = np.arange(len(label))
np.random.shuffle(index)
label = label[index]
data = data[index]
trX=data[:600]
trY=label[:600]
teX=data[600:]
teY=label[600:]
x = tf.placeholder(tf.float32, shape=(None, 1000))
y = tf.placeholder(tf.float32, shape=(None, 4))
model = dnn_model(input_dim=1000)
predictions = model(x)
sgd = SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Adadelta(),
metrics=['accuracy'])
model.fit(trX, trY, batch_size=batch_size, epochs=nb_epoch, shuffle=True) # validation_split=0.1
# model.save_weights('dnn_clean.h5')
score = model.evaluate(teX, teY, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
with sess.as_default():
adv_sample=[]
labels = labels[index]
teY_original = labels[230000:]
labels = keras.utils.to_categorical(labels, num_classes=None)
signals = signals[index]
signals = np.expand_dims(signals, axis=2)
trX = signals[:230000]
trY = labels[:230000]
teX = signals[230000:]
teY = labels[230000:]
print("Input label shape", shape(labels))
print("Input data shape", shape(signals))
model = dnn_model(input_dim=640)
x = tf.placeholder(tf.float32, shape=(None, 640, 1))
y = tf.placeholder(tf.float32, shape=(None, 17))
#################################logits########################################
predictions = model(x) ###### after softmax
predictions_logits = predictions.op.inputs[0] ###logits, before softmax
predictions = predictions_logits
#################################logits#######################################
#sgd = SGD(lr=0.0001, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss=keras.losses.categorical_crossentropy,
optimizer=keras.optimizers.Nadam(lr=0.002,
beta_1=0.9,
beta_2=0.999,
