|
We have moved to https://openmodeldb.info/. This new site has a tag and search system, which will make finding the right models for you much easier! If you have any questions, ask here: https://discord.gg/cpAUpDK |
Difference between revisions of "Beginner Training Guide"
m |
|||
| Line 3: | Line 3: | ||
=== Choosing a Fork === | === Choosing a Fork === | ||
| − | The original [https://github.com/xinntao/BasicSR/ BasicSR fork by Xinntao] still works fine for training. However, it lacks a lot of features and bug fixes that forks made by various community members have. Also, if you get the latest Xinntao fork you will be training a [[ESRGAN new-arch model]] instead of an [[ESRGAN old-arch model]]. This means you will not be able to train in scales other than 4. | + | The original [https://github.com/xinntao/BasicSR/ BasicSR fork by Xinntao] still works fine for training. However, it lacks a lot of features and bug fixes that forks made by various community members have. Also, if you get the latest Xinntao fork you will be training a [[ESRGAN new-arch model|new-arch model]] instead of an [[ESRGAN old-arch model|old-arch model]]. This means you will not be able to train in scales other than 4. |
If you are reading this guide as a refresher and currently use [https://github.com/victorca25/BasicSR Victorca25's fork], please consider switching to [https://github.com/BlueAmulet/BasicSR BlueAmulets fork]. It fixes many of the bugs present in Vic's fork (which is no longer being maintained) and has all the same features (and more). If this is your first time reading this guide, I still highly recommend [https://github.com/BlueAmulet/BasicSR BlueAmulets fork]. However, [https://github.com/dinjerr/BasicSR DinJerr's fork] is also a good alternative. | If you are reading this guide as a refresher and currently use [https://github.com/victorca25/BasicSR Victorca25's fork], please consider switching to [https://github.com/BlueAmulet/BasicSR BlueAmulets fork]. It fixes many of the bugs present in Vic's fork (which is no longer being maintained) and has all the same features (and more). If this is your first time reading this guide, I still highly recommend [https://github.com/BlueAmulet/BasicSR BlueAmulets fork]. However, [https://github.com/dinjerr/BasicSR DinJerr's fork] is also a good alternative. | ||
You can see a current list of [[Maintained BasicSR Forks|currently maintained forks here]]. | You can see a current list of [[Maintained BasicSR Forks|currently maintained forks here]]. | ||
Revision as of 05:53, 10 July 2020
Getting Started
This guide assumes you already know how to download/clone repositories from GitHub and that you are familiar with python and pip.
Choosing a Fork
The original BasicSR fork by Xinntao still works fine for training. However, it lacks a lot of features and bug fixes that forks made by various community members have. Also, if you get the latest Xinntao fork you will be training a new-arch model instead of an old-arch model. This means you will not be able to train in scales other than 4.
If you are reading this guide as a refresher and currently use Victorca25's fork, please consider switching to BlueAmulets fork. It fixes many of the bugs present in Vic's fork (which is no longer being maintained) and has all the same features (and more). If this is your first time reading this guide, I still highly recommend BlueAmulets fork. However, DinJerr's fork is also a good alternative.
You can see a current list of currently maintained forks here.
