Deep Learning

Collection of Common PyTorch Code Snippets

by
Collection of Common PyTorch Code Snippets

Click the above “Beginner’s Guide to Vision“, select to add “Star” or “Pin“ Heavyweight content delivered first-hand Zhang Hao: Master’s student at the School of Computer Science, Nanjing University, focusing on computer vision and machine learning, particularly visual recognition and deep learning. Personal homepage: http://lamda.nju.edu.cn/zhangh/ Original Zhihu link: https://zhuanlan.zhihu.com/p/59205847? This code is based on PyTorch … Read more

Ultimate Guide to Installing PyTorch 2.2 with GPU

by
Ultimate Guide to Installing PyTorch 2.2 with GPU

1. Deep Learning Workstation 1.1 Configuration First, here is the computer configuration diagram: Upgraded the configuration using the company’s office computer. Except for the graphics card and power supply, other hardware is original from the company computer. 1.2 Graphics Card If you have the budget, go directly for RTX4090, but cannot reuse the company computer … Read more

Visualizing PyTorch Deep Learning Training with tensorboardX

by
Visualizing PyTorch Deep Learning Training with tensorboardX

Click the above “Beginner’s Guide to Vision” to choose “Bookmark” or “Pin” Important resources delivered promptly Previously, I mentioned PyTorch’s dedicated visualization tool visdom, refer to the PyTorch deep learning training visualization tool visdom. However, many TensorFlow users were accustomed to using TensorBoard for training visualization. To enable PyTorch users to also use TensorBoard, developers … Read more

PyTorch Code Snippets Compilation for High Frequency Use

by
PyTorch Code Snippets Compilation for High Frequency Use

Source: About Data Analysis and Visualization This article is approximately 8000 words long and is recommended for a reading time of over 10 minutes. This article is a collection of commonly used code snippets for PyTorch, covering five aspects: basic configuration, tensor processing, model definition and operation, data processing, and model training and testing, along … Read more

Intelligent Prediction of Loose Circles in Deep Tunnels Based on Improved XGBoost Algorithm

by
Intelligent Prediction of Loose Circles in Deep Tunnels Based on Improved XGBoost Algorithm

Introduction Since the beginning of the 21st century, with the rapid development of the social economy, the demand for resources has continued to increase. However, shallow mineral resources are increasingly depleted, forcing mining work to shift underground. After blasting and excavating deep tunnels, the surrounding rock inevitably produces a loose circle due to the coupling … Read more

Is XGBoost Stronger Than Deep Learning?

by
Is XGBoost Stronger Than Deep Learning?

Why are tree-based machine learning methods, such as XGBoost and random forests, superior to deep learning on tabular data? This article provides reasons behind this phenomenon, selecting 45 open datasets and defining a new benchmark to compare tree-based models with deep models, summarizing three reasons to explain this phenomenon. Deep learning has made significant progress … Read more

Implementing Spectral Normalization GAN with PyTorch

by
Implementing Spectral Normalization GAN with PyTorch

Source: DeepHub IMBA This article is about 3800 words, and it is recommended to read in 5 minutes. Since the release of diffusion models, the attention and papers on GANs have decreased significantly, but some ideas within them are still worth understanding and learning. Therefore, in this article, we will implement SN-GAN using PyTorch. Spectral … Read more

What Is Generative AI and Is It a Pathway to AGI?

by
What Is Generative AI and Is It a Pathway to AGI?

You can “listen” to this article anytime on your mobile phone or computer Edge browser. Key Points: Generative AI, based on predictive models, can accurately perceive numbers, possess absolute mathematical knowledge and undeniable logic, and tirelessly reason to derive the best or optimal output based on current prompts. The tight connection between logic and the … Read more

Understanding Capsule Neural Networks

by
Understanding Capsule Neural Networks

Click on the above “Beginner’s Guide to Vision”, select to add “Bookmark” or “Pin” Important content delivered immediately From | Blog Garden Author | CZiFan Background Geoffrey Hinton is one of the pioneers of deep learning and the inventor of classic algorithms for neural networks like backpropagation. He and his team proposed a novel neural … Read more

The Development of CNN Architectures: From LeNet to EfficientNet

by
The Development of CNN Architectures: From LeNet to EfficientNet

Author: zzq https://zhuanlan.zhihu.com/p/68411179 This article is authorized, and unauthorized reproduction is not allowed. Introduction to Basic Components of CNN 1. Local Receptive Field In images, the connections between local pixels are relatively tight, while the connections between distant pixels are weaker. Therefore, each neuron does not need to perceive the entire image globally; it only … Read more