update examples/face_adversarial_attack/example/AFR.py.

修改了命名错误；包的顺序。

Signed-off-by: 君君臣臣君 <mingjun@isrc.iscas.ac.cn>

examples/face_adversarial_attack/example/AFR.py

@@ -15,20 +15,20 @@
 import os
 import re
 import numpy as np
-import matplotlib.image as mp
-import dlib
-import face_recognition as fr
-import face_recognition_models as frm
-from PIL import Image, ImageDraw
 import mindspore
+import mindspore.dataset.vision.py_transforms as P
 from mindspore.dataset.vision.py_transforms import ToPIL as ToPILImage
 from mindspore import Parameter, ops, nn, Tensor
 from mindspore.dataset.vision.py_transforms import ToTensor
-import mindspore.dataset.vision.py_transforms as P
-from loss_design import TrainOneStepCell, MyWithLossCell, FaceLossTargeTattack, FaceLossNoTargetAttack
+import dlib
+import matplotlib.image as mp
+import face_recognition as fr
+import face_recognition_models as frm
+from PIL import Image, ImageDraw
+from loss_design import MyTrainOneStepCell, MyWithLossCell, FaceLossTargetAttack, FaceLossNoTargetAttack
 from FaceRecognition.eval import get_net
 
-class Attack(object):
+class FaceAdversarialAttack(object):
     """
     Class used to create adversarial facial recognition attacks
     """
@@ -78,10 +78,10 @@ class Attack(object):
         if attack_method == "non-target attack":
             LOSS = FaceLossNoTargetAttack(self.target_emb)
         if attack_method == "target_attack":
-            LOSS = FaceLossTargeTattack(self.target_emb)
+            LOSS = FaceLossTargetAttack(self.target_emb)
 
         net_with_criterion = MyWithLossCell(self.resnet, LOSS, self.input_tensor)
-        train_net = TrainOneStepCell(net_with_criterion, self.opt)
+        train_net = MyTrainOneStepCell(net_with_criterion, self.opt)
 
         for i in range(2000):
 
@@ -133,28 +133,6 @@ class Attack(object):
         print("target_confidence:", self.target_emb.asnumpy()[0][target])
         print("input: %d, target: %d, adversarial: %d" % (input, target, adversarial))
 
-    def test1(self, adversarial_tensor):
-        self.adversarial_emb = self.resnet(
-            self.expand_dims((adversarial_tensor - self.MEAN[:, None, None]) / self.STD[:, None, None], 0))
-        self.input_emb = self.resnet(self.expand_dims(self.input_tensor, 0))
-        self.target_emb = self.resnet(self.expand_dims(self.target_tensor, 0))
-
-        adversarial = np.argmax(self.adversarial_emb.asnumpy())
-        target = np.argmax(self.target_emb.asnumpy())
-        input = np.argmax(self.input_emb.asnumpy())
-
-        print("input:", input)
-        print("input_confidence:", self.input_emb.asnumpy()[0][input])
-        print("================================")
-        print("adversarial:", adversarial)
-        print("adversarial_confidence:", self.adversarial_emb.asnumpy()[0][adversarial])
-        print("Confidence changes for input:", self.adversarial_emb.asnumpy()[0][input])
-        print("================================")
-        print("target:", target)
-        print("target_confidence:", self.target_emb.asnumpy()[0][target])
-        print("input:%d, target:%d, adversarial:%d" % (input, target, adversarial))
-
-
 
     def _reverse_norm(self, image_tensor):
         """