dlcv_for_beginners
1.0.0
Thank you for the various questions raised in the issue. Because it has not been updated for too long, I originally planned to concentrate on updating before the Spring Festival, but after reading it, I felt that I was unable to start. In addition, I had discussed with the editor of the book company that I should not release the second edition or reprinted version, so I decided to give up...
One of the errors I found myself is about the eigenvalues. SVD is not used for inverse definite matrices, but for asymmetric matrices. For details, please refer to the updated Zhihu answer: https://www.zhihu.com/question/20507061/answer/120540926 The errata in other parts is either already in errata.pdf, or everyone's discussion in issue is basically correct.
This repo is not expected to be updated again (frankly speaking, the second half of this book is outdated). If you have any questions, please send me a private message to me: yeyun11
I wish you all a happy Chinese New Year, New Year's Eve 2020
Originally named "Deep Learning and Computer Vision: An Introduction to Examples", please note: This book is positioned as an introduction .
Click here for the code. For downloading all color chart electronic versions, please refer to the online version of Chapter 5 and Chapter 6 for color charts: Chapter 5, Chapter 5, Chapter 6.
For some reasons I cannot understand, the English book in English was required by the publisher to forcefully translate. Finally: 1) Some English was translated into Chinese to varying degrees, and 2) The list of documents that accounted for the majority of English documents could not be included in the book. A list of citations is here.
Please come here for errors in the content. The errata is here.
Purchase link: JD.com, Amazon, Dangdang
Chapter 5: Examples of numpy and matplotlib visualization Chapter 6: Object detection annotation widget and local data enhancement widget Chapter 7: Two-dimensional plane classification, based on Caffe and MXNet respectively
Chapter 8: MNIST classification, based on Caffe and MXNet respectively
Chapter 9: Image chaos degree based on Caffe regression and convolution kernel visualization Chapter 10: Transfer learning of food classification models, confusion matrix, ROC curve drawing and model category response graph visualization, based on Caffe
Chapter 12: Using MNIST to train Siamese network, t-SNE visualization, based on Caffe
The book does not include miscellaneous: including manufacturing of adversarial samples (Caffe), two-dimensional GAN and training process visualization (PyTorch), automatic mosaic of pornographic images (Caffe), model fusion (Caffe), image segmentation (PyTorch)
Model pruning (PyTorch)
