“Pixel based galaxy morphology classification”的版本间差异

来自cluster
跳到导航 跳到搜索
(Created page with "This will update later. Here is the repository: https://github.com/Astro-Astre/Pixel-based_DeepLearningTechnic")
 
无编辑摘要
 
(未显示同一用户的5个中间版本)
第1行: 第1行:

This will update later.
==Introduction==
Here is the repository: https://github.com/Astro-Astre/Pixel-based_DeepLearningTechnic
This is a project about morphological galaxies classification. The amazing point is that we're researching an algorithm to seperate background and sources for decreasing the pollution.
==Dataset==
Training data comes from Legacy Survey in DECaLS region and the model will be applied to out DECaLS region (MzLS and BASS project).
==Labels==
[[File:Tree.png|150px|right|jumengting]]
Mike Walmsley trained on DECaLS region with GZD-1/2/5 catalog and GZD-5 class tree with active learning and then form a more confident catalog called catalog_auto. I set a threshold (e.g. 0.5) on each question to split and get labels of each picture. The GZD-5 label tree showed as follows.
==DECaLS introduction==
* The Dark Energy Camera (DECam) on the Blanco 4m telescope, located at the Cerro Tololo Inter-American Observatory.
==Out DECaLS introduction==

==Architecture==
*Simple CNN
*Dense Net
*Xception
==Loss function==
*Cross Entropy
*Focal loss

==Else==
Updating..

[https://github.com/Astro-Astre/Pixel-based_DeepLearningTechnic Here is the repository on Github]

2022年4月6日 (三) 05:41的最新版本

Introduction

This is a project about morphological galaxies classification. The amazing point is that we're researching an algorithm to seperate background and sources for decreasing the pollution.

Dataset

Training data comes from Legacy Survey in DECaLS region and the model will be applied to out DECaLS region (MzLS and BASS project).

Labels

jumengting

Mike Walmsley trained on DECaLS region with GZD-1/2/5 catalog and GZD-5 class tree with active learning and then form a more confident catalog called catalog_auto. I set a threshold (e.g. 0.5) on each question to split and get labels of each picture. The GZD-5 label tree showed as follows.

DECaLS introduction

  • The Dark Energy Camera (DECam) on the Blanco 4m telescope, located at the Cerro Tololo Inter-American Observatory.

Out DECaLS introduction

Architecture

  • Simple CNN
  • Dense Net
  • Xception

Loss function

  • Cross Entropy
  • Focal loss

Else

Updating..

Here is the repository on Github