jerryhero
jerryhero
I wanna to know how to use my own picture dataset to get the model which defenses Adversarial Attacks.How could I change the code to train my own dataset?
我想知道如何使用自己的图片数据集来训练支持对抗性样本防御的模型?不是那种标准数据集,如cifer和minst,而是我自己收集和标注的数据集。
when I load the plugin of "libunpacker.so". It prompt me loading successfully. but when I enter strings below. do_hookapitests com.android.providers.calendar It shows: teminate called after throwing an instance of 'std::invalid_argument'...
用图片训练好inception_v3模型后,再用其他图片做预测,为什么对于测试集样本,每次预测所属的类别经常变动?
请问你是在哪个sdk版本上测试的呢?xposed 模块和待测的demo apk分别是用的哪个版本sdk来编译的?