腾讯网

9个主流GAN损失函数的数学原理和Pytorch代码实现：从经典模型到现代变体

生成对抗网络(GANs)的训练效果很大程度上取决于其损失函数的选择。本研究首先介绍经典GAN损失函数的理论基础，随后使用PyTorch实现包括原始GAN、最小二乘GAN(LS-GAN)、Wasserstein GAN(WGAN)及带梯度惩罚的WGAN(WGAN-GP)在内的多种损失函数。 生成对抗网络(GANs)的工作原理 ...
雷锋网

GAN 很复杂？如何用不到 50 行代码训练 GAN（基于 PyTorch）

导语：GAN 比你想象的其实更容易。 编者按：上图是 Yann LeCun 对 GAN 的赞扬，意为“GAN 是机器学习过去 10 年发展中最有意思的想法。” 本文作者为前谷歌高级工程师、AI 初创公司 Wavefront 创始人兼 CTO Dev Nag，介绍了他是如何用不到五十行代码，在 PyTorch 平台上 ...
InfoWorld

Learn PyTorch: The best free online courses and tutorials

Deep learning continues to be one of the hottest fields in computing, and while Google’s TensorFlow remains the most popular framework in absolute numbers, Facebook’s PyTorch has quickly earned a ...
InfoWorld

PyTorch tutorial: Get started with deep learning in Python

Learn how to create a simple neural network, and a more accurate convolutional neural network, with the PyTorch deep learning library PyTorch is a Python-based tensor computing library with high-level ...
Visual Studio Magazine

Generating Synthetic Data Using a Generative Adversarial Network (GAN) with PyTorch

Dr. James McCaffrey of Microsoft Research explains a generative adversarial network, a deep neural system that can be used to generate synthetic data for machine learning scenarios, such as generating ...