gpt4 book ai didi

python - Receiving Assertion failed While generate adversarial samples 通过任何方法

转载 作者:行者123 更新时间:2023-11-28 18:57:13 24 4
gpt4 key购买 nike

我在通过任何方法生成对抗样本时收到以下错误

InvalidArgumentError: assertion failed: [] [Condition x <= y did not hold element-wise:x (Placeholder_173:0) = ] [[[[158 112 49]]]...] [y (Cast_6:0) = ] [1]
[[{{node assert_less_equal_1/Assert/AssertGuard/Assert}}]]

我的生成对抗样本的代码


from cleverhans.utils_keras import KerasModelWrapper
from cleverhans.attacks import FastGradientMethod
model=build_model()
sess = K.get_session()
wrap = KerasModelWrapper(model)
fgsm = FastGradientMethod(wrap, sess=sess)
fgsm_params = {'eps': 0.3,
'clip_min': 0.,
'clip_max': 1.}
adv_x = fgsm.generate_np(x_test, **fgsm_params)

模型代码在这里 tensorflow 版本 = 1.13.1

https://github.com/geifmany/cifar-vgg/blob/master/cifar10vgg.py

完整的堆栈跟踪

---------------------------------------------------------------------------
InvalidArgumentError Traceback (most recent call last)
~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1333 try:
-> 1334 return fn(*args)
1335 except errors.OpError as e:

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _run_fn(feed_dict, fetch_list, target_list, options, run_metadata)
1318 return self._call_tf_sessionrun(
-> 1319 options, feed_dict, fetch_list, target_list, run_metadata)
1320

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _call_tf_sessionrun(self, options, feed_dict, fetch_list, target_list, run_metadata)
1406 self._session, options, feed_dict, fetch_list, target_list,
-> 1407 run_metadata)
1408

InvalidArgumentError: assertion failed: [] [Condition x <= y did not hold element-wise:x (Placeholder_173:0) = ] [[[[158 112 49]]]...] [y (Cast_6:0) = ] [1]
[[{{node assert_less_equal_1/Assert/AssertGuard/Assert}}]]

During handling of the above exception, another exception occurred:

InvalidArgumentError Traceback (most recent call last)
<ipython-input-4-8941aeed68c9> in <module>
8 'clip_min': 0.,
9 'clip_max': 1.}
---> 10 adv_x = fgsm.generate_np(x_test, **fgsm_params)

~/anaconda3/lib/python3.7/site-packages/cleverhans/attacks/__init__.py in generate_np(self, x_val, **kwargs)
201 feed_dict[new_kwargs[name]] = feedable[name]
202
--> 203 return self.sess.run(x_adv, feed_dict)
204
205 def construct_variables(self, kwargs):

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in run(self, fetches, feed_dict, options, run_metadata)
927 try:
928 result = self._run(None, fetches, feed_dict, options_ptr,
--> 929 run_metadata_ptr)
930 if run_metadata:
931 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
1150 if final_fetches or final_targets or (handle and feed_dict_tensor):
1151 results = self._do_run(handle, final_targets, final_fetches,
-> 1152 feed_dict_tensor, options, run_metadata)
1153 else:
1154 results = []

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
1326 if handle is None:
1327 return self._do_call(_run_fn, feeds, fetches, targets, options,
-> 1328 run_metadata)
1329 else:
1330 return self._do_call(_prun_fn, handle, feeds, fetches)

~/anaconda3/lib/python3.7/site-packages/tensorflow/python/client/session.py in _do_call(self, fn, *args)
1346 pass
1347 message = error_interpolation.interpolate(message, self._graph)
-> 1348 raise type(e)(node_def, op, message)
1349
1350 def _extend_graph(self):

InvalidArgumentError: assertion failed: [] [Condition x <= y did not hold element-wise:x (Placeholder_173:0) = ] [[[[158 112 49]]]...] [y (Cast_6:0) = ] [1]
[[node assert_less_equal_1/Assert/AssertGuard/Assert (defined at /home/munib/anaconda3/lib/python3.7/site-packages/cleverhans/utils_tf.py:615) ]]


最佳答案

看起来您的输入不在 [clip_min, clip_max] 区间内。在 x_test 提供给 generate_np 之前,您是否确保将其剪裁到该间隔?

关于python - Receiving Assertion failed While generate adversarial samples 通过任何方法,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/56876874/

24 4 0
Copyright 2021 - 2024 cfsdn All Rights Reserved 蜀ICP备2022000587号
广告合作:1813099741@qq.com 6ren.com