登录
首页 » python » CNN二分类

CNN二分类

于 2022-03-22 发布 文件大小:43.45 kB
0 133
下载积分: 2 下载次数: 1

代码说明:

cifar_10代码,实现二分类,python语言编写,可在多种框架内实现:如Tensorlow、Caffe等。可以作为一个独立的算法使用。包中自带测试数据集,为标准的多示例数据集,通过扩展可以进行训练和测试任务。

下载说明:请别用迅雷下载,失败请重下,重下不扣分!

发表评论

0 个回复

  • DCGAN的Tensorflow算法实现
    对抗性生成网络(GAN)是近年来提出的一种神经网络,有重要应用和深入研究。DCGAN (Deep Convolutional Generative Adversarial Networks)是DCGAN的Tensorflow实现。
    2022-05-06 11:25:08下载
    积分:1
  • LinkPrediction
    链路预测程序,Python源代码(link prediction)(Link prediction program, Python source code (link prediction))
    2020-07-03 02:00:02下载
    积分:1
  • python_arima
    1.获取被观测系统时间序列数据; 2.对数据绘图,观测是否为平稳时间序列;对于非平稳时间序列要先进行d阶差分运算,化为平稳时间序列; 3.经过第二步处理,已经得到平稳时间序列。要对平稳时间序列分别求得其自相关系数ACF 和偏自相关系数PACF ,通过对自相关图和偏自相关图的分析,得到最佳的阶层p和阶数q 4.由以上得到的d(差分次数)、q(阶层数)、p(阶数) ,得到ARIMA模型。然后开始对得到的模型进行模型检验。
    2022-08-23 22:13:18下载
    积分:1
  • 移动山峰基准
    bvmbvmnvnmm bmnmbbb
    2023-08-30 11:45:02下载
    积分:1
  • tests
    说明:  python core test files
    2019-06-01 11:41:19下载
    积分:1
  • 错题1
    PYTHON易错题;二级PYTHON易错题;PYTHON易错题;PYTHON易错题(PYTHON is prone to errors, PYTHON is prone to errors , PYTHON is prone to errors,PYTHON is prone to errors.)
    2020-06-15 22:25:02下载
    积分:1
  • WaterProject
    说明:  水体提取功能,里面主要实现了多源遥感卫星水体提取,入库,推送等后续代码功能(Water extraction function, which mainly realizes the multi-source remote sensing satellite water extraction, storage, push and other follow-up code functions)
    2021-03-06 18:30:31下载
    积分:1
  • object-intersection
    blender script to make a object intersection
    2014-01-12 21:59:12下载
    积分:1
  • 基于深度学习字符型图片数字验证码识别完整过程及Python实现(深度学习学习、实现数字、字符模型训练、详细介绍附源码)
    基于深度学习字符型图片数字验证码识别完整过程及Python实现(深度学习学习、实现数字、字符模型训练、详细介绍附源码)
    2019-06-19下载
    积分:1
  • kaggle_diabetic-master
    说明:  A commented bash script to generate our final 2nd place solution can be found in make_kaggle_solution.sh. Running all the commands sequentially will probably take 7 - 10 days on recent consumer grade hardware. If you have multiple GPUs you can speed things up by doing training and feature extraction for the two networks in parallel. However, due to the computationally heavy data augmentation it may be far less than twice as fast especially when working with 512x512 pixel input images. You can also obtain a quadratic weighted kappa score of 0.839 on the private leaderboard by just training the 4x4 kernel networks and by performing only 20 feature extraction iterations with the weights that gave you the best MSE validation scores during training. The entire ensemble only achieves a slightly higher score of 0.845.
    2019-05-11 15:31:21下载
    积分:1
  • 696516资源总数
  • 106914会员总数
  • 0今日下载