Tag：deep learning
-
YOLOv5 source code line by line super-detailed comments and interpretation – project directory structure analysis
catalogs preamble I. Project catalog structure 1.1 .github folder 1.2 datasets 1.3 data folder 1.4 models folder 1.5 runs folder 1.6 utils folder 1.7 Other first-level catalog documents I. Project catalog structure After downloading the source code and configuring the environment, you can see the overall directory of YOLOv5 as shown above. Let’s analyze them […]
-
Stable Diffusion model principle and realization process (with commonly used model website, download method)
catalogs preamble What is the Stable Diffusion model? Stable Diffusion works: Application Scenarios for Stable Diffusion Modeling Stable Diffusion free use site stability.ai: Local deployment of Stable Diffusion methods: StableDiffusion Chinese Blogger Introduction: Specializing in front and back end, machine learning, artificial intelligence applications development of quality creators, adhering to the spirit of the Internet […]
-
Image Recognition and Classification: A Practical Guide
Image recognition and classification is one of the core tasks in the field of computer vision. It involves recognizing objects, scenes, or concepts in an image and assigning them to predefined categories. In this article, we will introduce you to the basic concepts of image recognition and classification, and demonstrate how to implement image recognition […]
-
ImportError: cannot import name ‘Literal‘ from ‘typing‘ (D:\Anaconda\envs\tensorflow\lib\typing.py)
Reporting Errors Background: I downgraded python 3.8 to 3.7 in my original newly created anaconda environment (mine is named tensorflow) because the tensorflow-gpu version needs to be installed. The following error occurs when importing the seaborn package: ImportError: cannot import name ‘Literal’ from ‘typing’ (D:\Anaconda\envs\tensorflow\lib\typing.py) Cause analysis: This is due to the fact that ‘Literal’ […]
-
Building Neural Networks with PyTorch
PyTorch Deep Learning in Action (3) – Building Neural Networks with PyTorch 0. Preface1. PyTorch building neural network first experience1.1 Building Neural Networks with PyTorch1.2 Neural network data loading1.3 Model testing1.4 Getting the value of the middle layer 2. Using Sequential Classes to Build Neural Networks3. Saving and loading PyTorch models3.1 Components required for model […]
-
Neural Networks and Model Training Process in Detail
PyTorch Deep Learning in Action (1) – Neural Network and Model Training Process in Detail 0. Preface1. Traditional machine learning and artificial intelligence2. Basics of artificial neural networks2.1 Artificial Neural Network Composition2.2 Training of Neural Networks 3. Forward dissemination3.1 Calculating hidden layer values3.2 Perform nonlinear activation3.3 Calculating the output layer values3.4 Calculation of the value […]
-
[NLP] Tutorial on fine-tuning using Alpaca-Lora based on the llama model
Stanford Alpaca is fine-tuning on the whole model of LLaMA, i.e., all parameters in the pre-trained model are fine-tuned (full fine-tuning). However, this method still requires high hardware cost and is inefficient for training. [NLP] Understanding Efficient Fine-Tuning of Large Language Models (PEFT) Therefore, Alpaca-Lora utilizes the Lora technique by adding additional network layers to […]
-
Deep Learning – Convolutional Neural Network (CNN) Theory
Study period: 2022.04.10~2022.04.12 Article Catalog 3. Convolutional neural network CNN3.1 Concept of Convolutional Neural Networks3.1.1 What is a CNN?3.1.2 Why use CNNs?3.1.3 Principles of human vision 3.2 Fundamentals of CNN3.2.1 Main structures3.2.2 Convolution layer1. Convolutional operations2. Three modes of convolution3. The nature of convolution 3.2.3 Pooling layer3.2.4 Activation layer3.2.5 Rasterization3.2.6 Full connectivity layer3.2.7 Reverse propagation3.2.8 […]
-
Python’s method for importing torch packages
Article Catalog preambleI. What is Pythorch?Second, how to download and import the torch package?Third, pip package manager download failure torch, the solution and the official website to download teaching1. Download failure, solution2.Official website download Fourth, why there will be the official website to download and local direct download, torch two ways?summarize preamble With the continuous […]
-
OpenAI’s Artificial Intelligence Speech Recognition Model Whisper Explained and Used
1 whisper Introduction OpenAI, the company that owns the ChatGPT language model, has open-sourced the Whisper automated speech recognition system, and OpenAI emphasizes that Whisper’s speech recognition ability has reached the human level. Whisper is a general-purpose speech recognition model trained using a large amount of multilingual and multi-task supervised data, capable of achieving near-human […]