pytorch tutorial -- DCGAN

本文详细介绍了DCGAN(深度卷积生成对抗网络)的工作原理,包括生成器和判别器的角色。训练过程中,生成器试图生成逼真的假图像,而判别器则试图区分真实图像和生成的假图像。随着训练的进行,最终目标是生成器能产生与训练数据分布相同的完美假图像,判别器判断真假的概率为50%。文章还涵盖了网络定义、损失函数、训练策略以及可视化技巧。
摘要由CSDN通过智能技术生成
  • About GAN

    1. GANs is a framework for teaching DL model to capture data’s distribution so we can generate new data from that same distribution.
    2. The job of the generator is to spawn ‘fake’ images that look like the training images.
    3. The job of the discriminator is to look at an image and output whether or not it is a real training image or a fake image from the generator.
    4. The equilibrium of this game is when the generator is generating perfect fakes that look as if they came directly from the training data, and the discriminator is left to always guess at 50% confidence that the generator output is real or fake.
    5. D(x) is the discriminator network which outputs the (scalar) probability that x came from training data rather than the generator. D(x) can also be thought of as a traditional binary classifier.
    6. (z) represents the generator function which maps the latent vector z to data-space. The goal of G is to estimate the distribution that the training data comes from (pdata) so it can generate fake samples from that estimated distribution (pg).
    7. G play a minimax game in which D tries to maximize the probability it correctly classifies reals and fakes (logD(x)), and G tries to minimize the probability that D will predict its outputs are fake (log(1−D(G(x)))).
    8. In t
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值