PART01 Concept of Deep Learning Deep Learning (DL) was first proposed by G. E. Hinton and others at the University of Toronto in 2006. It is a machine learning (ML) process that derives a deep network structure with multiple layers based on sample data through certain training methods. Machine learning typically analyzes structured data using … Read more
Selected from Matrices.io Author: Florian Courtial Translated by Machine Heart Source: Robot Heart Contributors: Li Zenan, Jiang Siyuan The popular deep learning framework TensorFlow (The Chinese official account of TensorFlow was launched earlier this month) is built on C++, but the vast majority of people develop their models using TensorFlow in Python. With the improvement … Read more
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
In the field of deep learning, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Deep Neural Networks (DNN) are the three most widely researched and applied neural network models. They each have their own focus in terms of structure, function, and applicable scenarios, complementing each other. This article will provide a detailed analysis of … Read more
1. Installing TensorFlow 1. Install from Binary using pip Note: The link to the latest version of the binary files can be obtained from the TensorFlow official website here. Please install the latest version of pip, or use pip install –upgrade pip to update. If installing the GPU version, please ensure that CUDA is installed … Read more
Introduction The main difference between the CPU version and the GPU version is the running speed; the GPU version runs faster. Therefore, if your computer’s graphics card supports CUDA, it is recommended to install the GPU version. The CPU version requires no additional preparation and can generally be installed on any computer without needing a … Read more
1 Configuration Issues (1). For computers equipped with a GPU and a need for deep learning, set up a usable and clean deep learning environment. (2). Configure with Anaconda3 + CUDA10.0 + CuDNN + Pytorch1.2 + Pycharm. (3). Resolve the issue of not being able to use the torchvision library in Pytorch. 2 Setup Process … Read more