Face recognition system - Artificial intelligence recognition core based on Python
I've been addicted to Python programming since I wrote an order system with Python + Django. Just a few days ago, the boss of the company asked me to study face recognition, so I wrote a core of face recognition system in Python for the whole system later.
Computer Vision Tutorial 0-3: Why do Photos have death angles? Detail the camera matrix and distortion
Make writing a habit together! This is the sixth day of my participation in the "Gold Digging Day New Plan · April More text Challenge". Click here for more details. Today we'll talk about camera matrix and distortion
MobileNet combat: TensorFlow2.x version, MobileNetV1 image classification task (large data set)
Make writing a habit together! This is the sixth day of my participation in the "Gold Digging Day New Plan · April More text Challenge". Click here for more details. Here we have a tensor from the seedling data set, and we have 12 different kinds of data sets
StackGAN++: Realistic Image Synthesis with Stacked GAN
Make writing a habit together! This is the third day of my participation in the "Gold Digging Day New Plan · April More text Challenge". Click here for more details. StackGAN++: Realistic Image Synthesis with StackedGAN
Convolutional neural networks in the 2020s
ConvNeXt provides guidance for the design of convolutional networks in the post-VIT era, and its influence on the design paradigm of convolutional neural networks in the 2020s and subsequent convolutional neural networks will be immeasurable, perhaps starting a new ConvNet design paradigm innovation.
Exponentially accelerated architecture search: CMU proposes a differentiable architecture search method based on gradient descent
Adapted from arXiv by Hanxiao Liu, Karen Simonyan and Yiming Yang. According to the researchers, this method has been proven to achieve industry-best results on both convolutional and recurrent neural networks, and the GPU computing power is sometimes only 700 times that of previous search methods, meaning that a single GPU can complete the task. The theory of the study...
Instead of advanced principles, let's talk about machine learning in simple language
@toc ✨ Blogger introduction ?️ Introduction Machine learning everyone is talking about it, but apart from teachers who know what it is, very few people can explain what it is. If you read online articles about machine learning, you're likely to come across one of two things: a thick academic trilogy filled with theorems (I got it
"Artificial Intelligence Sharing" in Xiamen GDG 2018
A horde of eager GDgers. At 9:00, The activity officially began. Yang Qiang, Deputy Secretary of Information School of Xiamen University, xu Chunhang, Deputy Director of software Park Management Office of Torch Park Management Committee, gave a short speech. Zheng Lingxiang and Shan Linjie introduced GDG DevFest, Sino-US Young Maker Exchange Center, Xiamen Google Developer Community, and Mais Plan respectively. And Women Techmakers...
Deep Learning 005- Solving dichotomies in a few lines of Keras code
Many articles and textbooks use the MNIST dataset as the "Hello World" program for deep learning, but this dataset has one big feature: it is a typical multi-classification problem (there are 10 categories in total). When we first started to get into deep learning, I thought we should start with the simplest dichotomy problem. In terms of deep learning frameworks, the popular one is Tens...
What are the obstacles to realizing the value of AI?
Ai has huge potential for global businesses. But flawed strategies, poor process change methods, a lack of expertise, and a general lack of understanding of technology mean that many businesses remain unable to derive value from AI. What are the obstacles to realizing the value of AI? To realize person