2503-郑同学-算法方向-计算机视觉-就业:是 扫二维码继续学习 二维码时效为半小时

(0评价)
价格: 免费

数据标准化,把它变成标准分布。

[展开全文]

Step 1:创建自定义数据集

[展开全文]

w = torch.rand(16, 3, 5, 5)

= (ker_num, input_channel, ker_size, ker_size)

[展开全文]

Input_channels:

  • 黑白:1
  • 彩色:3
[展开全文]

Stocastic: 随即筛选样本

 

[展开全文]

val_set: for detecting overfitting

[展开全文]

.matmul() 取后两维相乘

 

[展开全文]

unsqueeze:

正:在之前插入

负:在之后插入

[展开全文]

.index_select(0, [0, 2])

 

[展开全文]

torch.tensor([2., 3.2])

torch.FloatTensor(2, 3)

 

Unintialized: 未初始化的tensor

 

增强学习一般用 DoubleTensor

[展开全文]

Sequence Generation

Conditional Sequence Generation

Maximizing Expected Reward

Policy Gradient

Conditional GAN

 

Abtractive Summarization

 

[展开全文]

Feature Extraction:

InfoGAN

VAE-GAN

BiGAN

Triple GAN

 

Feature Disentangle  v. 解开

 

 

 

[展开全文]

J-S divergence proplem

 

Wasserstein GAN:

Earth Mover's Distance

 

Lipschitz Function

intractable adj. 棘手的 <==> difficult

 

 

[展开全文]

f-divergence

exponential  adj. 指数

 

 

[展开全文]

Theory behind GAN:

Divergence

KL Divergence

sample v. 抽样

J-S divergence

 

[展开全文]

Unsupervised Conditional Generation

  • Direct Transfomation
  • Projection to Common Space:

CycleGAN:

Cycle consistency

[展开全文]