原创 Pre-training on Grayscale ImageNet Improves Medical Image Classification

Pre-training on Grayscale ImageNet Improves Medical Image Classification Paper:http://openaccess.thecvf.com/content

原创 決策樹和隨機森林原理(Decision Trees and Random Forests)

決策樹和隨機森林原理(Decision Trees and Random Forests) 決策樹是一種樹的數據結構的 if-then語句的體現;隨機森林是決策樹的組合。 (項目學習筆記及代碼) 一、決策樹 1、目標 數據結構中的

原创 Reptile: On First-Order Meta-Learning Algorithms

On First-Order Meta-Learning Algorithms Paper:https://arxiv.org/pdf/1803.02999.pdf Code:https://github.com/openai/s

原创 patch-GAN(pixel2pixel):Image-to-Image Translation with Conditional Adversarial Networks

Image-to-Image Translation with Conditional Adversarial Networks Paper:https://arxiv.org/pdf/1611.07004.pdf Code:ht

原创 範數的數學意義

L0,L1,L2範數的數學意義 (如有不當,敬請斧正) Tips: 範數所表示的一些數學意義:衆數,中位數,均值 A:\mathcal{A:}A: L0範數:求L0範數最小時,表示的是數據中的衆數modes(假設00=00^0

原创 Pytorch之卷積神經網絡(Mnist)學習

Pytorch之Mnist學習 以前寫的代碼太差,而代碼的書寫和可讀性很重要,同時想掌握兩個Deep Learning的框架,在此學習記錄。閱讀的代碼是pytorch官方給的例子:https://github.com/pytorc

原创 f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization

fff-GAN: Training Generative Neural Samplers using Variational Divergence Minimization Paper:http://papers.nips.cc/

原创 DCGAN:Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Paper:https://arxiv.or

原创 Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Skip Connections

Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections Papers: Ni