-
Chapter2
各种基础深度学习程序,识别图片,线性回归,等一系列(Various Basic Deep Learning Procedures)
- 2020-06-22 21:00:01下载
- 积分:1
-
Pytorch implementation of Generative Adversarial Networks
# pytorch-MNIST-CelebA-GAN-DCGAN
Pytorch implementation of Generative Adversarial Networks (GAN) [1] and Deep Convolutional Generative Adversarial Networks (DCGAN) [2] for MNIST [3] and CelebA [4] datasets.
* If you want to train using cropped CelebA dataset, you have to change isCrop = False to isCrop = True.
* you can download
- MNIST dataset: http://yann.lecun.com/exdb/mnist/
- CelebA dataset: http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html
* pytorch_CelebA_DCGAN.py requires 64 x 64 size image, so you have to resize CelebA dataset (celebA_data_preprocess.py).
* pytorch_CelebA_DCGAN.py added learning rate decay code.
## Implementation details
* GAN
![GAN](pytorch_GAN.png)
* DCGAN
![Loss](pytorch_DCGAN.png)
## Resutls
### MNIST
- 2022-03-21 10:01:59下载
- 积分:1
-
VAE
说明: VAE程序复现,速度快,清晰准确,mnist手写数据集和(VAE program replay, fast, clear and accurate, mnist handwritten data set and)
- 2020-01-16 13:05:45下载
- 积分:1
-
Deep Learning With Python中文版
Deep Learning With Python_中文版 --本书由Keras之父、现任Google人工智能研究员的弗朗索瓦?肖莱(Franc?ois Chollet)执笔,详尽介绍了用Python和Keras进行深度学习的探索实践,包括计算机视觉、自然语言处理、产生式模型等应用。书中包含30多个代码示例,步骤讲解详细透彻。(Chinese Version - This book is written by Franc OIS Chollet, the father of Keras and current researcher of Google Artificial Intelligence. It introduces in detail the exploratory practice of in-depth learning with Python and Keras, including computer vision, natural language processing, production model and other applications. The book contains more than 30 code examples with detailed steps.)
- 2019-02-25 18:00:50下载
- 积分:1
-
用Python设计芯片
说明: 使用Python语言在数字设计中,有很多优势比如算法建模,RTL模板生成等优势(Use Python in ASIC design)
- 2021-04-24 12:28:47下载
- 积分:1
-
NNTest (2)
说明: 人工神经网络实验,采用RBF神经网络实现函数的拟合(In the experiment of artificial neural network, RBF neural network is used to realize the function fitting)
- 2020-12-01 10:23:45下载
- 积分:1
-
python-notes22
pythonintroductionandnotes
- 2018-01-20 15:45:43下载
- 积分:1
-
mnist识别
说明: 利用卷积神经网络及神经网络识别手写数字,准确率95以上。(Using convolution neural network and neural network to recognize handwritten digits, the accuracy is over 95.)
- 2019-03-19 15:29:06下载
- 积分:1
-
Django实战代码(7月26日)
说明: 开发一个培训收费网站的代码文件,供大家参考学习(code sampleb for a web service ,just like learning)
- 2020-06-29 11:00:02下载
- 积分:1
-
scalechange
进制转换,可实现2-16进制任意进制数间相互转换(Hex conversion, 2-16 hex convert any decimal number between)
- 2012-05-29 16:59:01下载
- 积分:1