![](https://img-blog.csdnimg.cn/20201014180756927.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
面向编程人员的实用深度学习
文章平均质量分 79
Klein&Macmillan
博主很懒,什么都不想告诉你
展开
-
Testimonials
Get startedStart watching lesson 1 now!The Economist“This month fast.ai, an education non-profit based in San Francisco, kicked off the third year of its course in deep learning. Since its inception it has attracted more than 100,000 students, scattered ar原创 2024-06-06 08:47:26 · 738 阅读 · 0 评论 -
Kaggle
Kaggle is the world’s largest data science community. One of Kaggle’s features is “Notebooks”, which is “a cloud computational environment that enables reproducible and collaborative analysis”. In particular, Kaggle provides access to GPUs for free. Every原创 2024-06-03 08:38:51 · 865 阅读 · 0 评论 -
Forums
If you need help, there’s a wonderful online community ready to help you at forums.fast.ai. Before asking a question on the forums, search carefully to see if your question has been answered before. (The forum system won’t let you post until you’ve spent a原创 2024-06-03 08:38:10 · 381 阅读 · 0 评论 -
The book
section.原创 2024-05-31 10:06:22 · 248 阅读 · 0 评论 -
25、潜伏扩散(Latent diffusion)
Video。原创 2024-05-31 09:08:41 · 139 阅读 · 0 评论 -
24、注意力和变压器(Attention & transformers)
rearrange。原创 2024-05-29 15:51:31 · 401 阅读 · 0 评论 -
23、超分辨率(Super-resolution)
In this lesson, we work with Tiny Imagenet to create a super-resolution U-Net model, discussing dataset creation, preprocessing, and data augmentation. The goal of super-resolution is to scale up a low-resolution image to a higher resolution. We train the原创 2024-05-29 15:50:12 · 1524 阅读 · 0 评论 -
22、Karras et al (2022)
Jeremy begins this lesson with a discussion of improvements to the DDPM/DDIM implementation. He explores the removal of the concept of an integral number of steps, making the process more continuous. He then delves into predicting the amount of noise in an原创 2024-05-28 08:38:47 · 666 阅读 · 0 评论 -
21、DDIM
In this lesson, Jeremy, Johno, and Tanishq discuss their experiments with the Fashion-MNIST dataset and the CIFAR-10 dataset, a popular dataset for image classification and generative modeling. They introduce Weights and Biases (W&B), an experiment trackin原创 2024-05-28 08:37:58 · 284 阅读 · 0 评论 -
20、混合精度(Mixed Precision)
In this lesson, we dive into mixed precision training and experiment with various techniques. We introduce the MixedPrecision callback for PyTorch and explore the Accelerate library from HuggingFace for speeding up training loops. We also learn a sneaky tr原创 2024-05-27 15:40:14 · 458 阅读 · 0 评论 -
19、DDPM和辍学(DDPM and Dropout)
In this lesson, Jeremy introduces Dropout, a technique for improving model performance, and with special guests Tanishq and Johno he discusses Denoising Diffusion Probabilistic Models (DDPM), the underlying foundational approach for diffusion models. The l原创 2024-05-27 15:39:29 · 261 阅读 · 0 评论 -
18、加速SGD和ResNets(Accelerated SGD & ResNets)
In this lesson, we dive into various stochastic gradient descent (SGD) accelerated approaches, such as momentum, RMSProp, and Adam. We start by experimenting with these techniques in Microsoft Excel, creating a simple linear regression problem and applying原创 2024-05-24 15:21:55 · 322 阅读 · 0 评论 -
17、初始化/规范化(Initialization/normalization)
In this lesson, we discuss the importance of weight initialization in neural networks and explore various techniques to improve training. We start by introducing changes to the miniai library and demonstrate the use of HooksCallback and ActivationStats for原创 2024-05-24 15:21:03 · 283 阅读 · 0 评论 -
16、学习者框架(The Learner framework)
In Lesson 16, we dive into building a flexible training framework called the learner. We start with a basic callbacks Learner, which is an intermediate step towards the flexible learner. We introduce callbacks, which are functions or classes called at spec原创 2024-05-17 13:21:47 · 776 阅读 · 0 评论 -
15、自动编码器(Autoencoders)
We start with a dive into convolutional autoencoders and explore the concept of convolutions. Convolutions help neural networks understand the structure of a problem, making it easier to solve. We learn how to apply a convolution to an image using a kernel原创 2024-05-17 13:20:33 · 407 阅读 · 0 评论 -
14、反向传播(Backpropagation)
【代码】14、反向传播(Backpropagation)原创 2024-05-16 09:00:50 · 284 阅读 · 0 评论 -
13、反向传播和MLP(Backpropagation & MLP)
【代码】13、反向传播和MLP(Backpropagation & MLP)原创 2024-05-16 08:59:30 · 347 阅读 · 0 评论 -
12、均移聚类(Mean shift clustering)
In this lesson, we start by discussing the CLIP Interrogator, a Hugging Face Spaces Gradio app that generates text prompts for creating CLIP embeddings. We then dive back into matrix multiplication, using Einstein summation notation and torch.einsum to sim原创 2024-05-15 09:08:53 · 435 阅读 · 0 评论 -
11、矩阵乘法(Matrix multiplication)
In this lesson, we discuss various techniques and experiments shared by students on the forum, such as interpolating between prompts for visually appealing transitions and improving the update process in text-to-image generation, and a novel approach to de原创 2024-05-15 09:08:03 · 437 阅读 · 1 评论 -
10、深入挖掘(Diving Deeper)
【代码】10、深入挖掘(Diving Deeper)原创 2024-05-14 11:07:07 · 484 阅读 · 0 评论 -
9、稳定扩散(Stable Diffusion)
score。原创 2024-05-14 11:06:00 · 300 阅读 · 0 评论 -
摘要Summaries--课时八(Lesson 8)
Building embeddings from scratch原创 2024-05-13 13:12:02 · 1583 阅读 · 0 评论 -
摘要Summaries--课时七(Lesson 7)
Gradient accumulation and GPU memory原创 2024-05-13 13:09:34 · 1433 阅读 · 0 评论 -
摘要Summaries--课时六(Lesson 6)
【代码】摘要Summaries--课时六(Lesson 6)原创 2024-05-11 08:52:36 · 696 阅读 · 0 评论 -
摘要Summaries--课时五(Lesson 5)
Linear model and neuralnet from scratch原创 2024-05-11 08:51:38 · 614 阅读 · 0 评论 -
摘要Summaries--课时四(Lesson 4)
New and Exciting Content Why Hugging Face transformer Will we in this lecture fine-tune a pretrained NLP model with HF rather than fastai library? Why use transformer rather than fastai library? Is Jeremy in the process of integrating transformer int原创 2024-05-10 08:46:04 · 862 阅读 · 0 评论 -
摘要Summaries--课时三(Lesson 3)
Introduction and survey “Lesson 0” How to fast.ai Where is Lesson 0 video? What does it to do with the book ‘meta learning’ and fastai course? How to do a fastai lesson? Watch with note Run the notebook and experiment Reproduce the notes from t原创 2024-05-10 08:44:13 · 671 阅读 · 0 评论 -
摘要Summaries--课时二(Lesson 2)
Daniel 深度碎片。原创 2024-05-09 09:02:42 · 754 阅读 · 0 评论 -
摘要Summaries--课时一(Lesson 1)
Daniel 深度碎片。原创 2024-05-09 09:00:54 · 320 阅读 · 0 评论 -
奖励:数据伦理(Bonus: Data ethics)
Video。原创 2024-05-08 08:52:40 · 1253 阅读 · 0 评论 -
8、卷积Convolutions (CNN)
embeddingsVideoResources。原创 2024-05-08 08:51:26 · 370 阅读 · 0 评论 -
7、协同过滤(Collaborative filtering)
VideoResources。原创 2024-05-07 17:31:39 · 363 阅读 · 0 评论 -
6、随机森林(Random forests)
Video。原创 2024-05-07 17:30:50 · 286 阅读 · 0 评论 -
从头开始的模型(From-scratch model)
sigmoidmetricsVideo。原创 2024-05-06 16:42:32 · 732 阅读 · 0 评论 -
自然语言(NLP)
VideoResources。原创 2024-05-06 16:41:03 · 463 阅读 · 0 评论 -
神经网络基础(Neural net foundations)
(ReLU).Video。原创 2024-04-30 08:48:59 · 361 阅读 · 0 评论 -
部署(Deployment)
Video。原创 2024-04-30 08:47:28 · 406 阅读 · 1 评论 -
实用深度学习(Practical Deep Learning)
New!Welcome!Lessonsnot。原创 2024-04-29 09:15:36 · 1173 阅读 · 0 评论 -
入门(Getting started)
VideoResources。原创 2024-04-29 09:24:36 · 568 阅读 · 0 评论