- 博客(4)
- 收藏
- 关注
原创 2021-10-28 | 读Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
动机 Sparse adversarial attacks can fool deep neural networks (DNNs) by only perturbing a few pixels (regularized by‘0norm). Recent efforts combine it with another‘∞imperceptible on the pertur- bation magnitudes. The resultant sparse and im- perceptible at
2021-10-29 19:59:16 426
原创 三天打鱼两天晒网的作业 | 欢迎批评指正
D:\zxqaq\app\Anaconda\envs\pytorch\python.exe "D:/zxqaq/Documents/week2_logistic regression/main.py" y = [1], it's a 'cat' picture. Number of training examples: m_train =209 Number of testing examples: m_test = 50 Height / width of each image: num_px .
2021-09-16 00:49:08 135
原创 Machine Learning - Andrew Ng | 网课笔记
Definition ofMachine Learning T-TASK P-PARAMETER E-EXPERIENCE Supervised Learning 回归问题(连续值) 分类问题(离散值) Unsupervised Learning clustering(聚类) cocktail party problem Linear Regression 即线性回归要寻找代价函数的最低点,使假设函数hypothesis 与 真实值...
2021-08-12 18:22:22 95
原创 Context Encoders | PBL踩坑中QAQ
在pycharm中选择anaconda环境 tensorflow和pytorch都要下载gpu版本 Context Encoder pycharm中新建项目 train_images下放arch文件夹存放训练图片 修复的图片自动保存在images文件夹中 头文件 import glob import cv2 import os import matplotlib.pyplot as plt #import tensorflow as tf import tensorflow.compa.
2021-08-09 10:48:37 773 4
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人