Commit graph

Select branches

Hide pull requests

master

Mono Color

• d0785e12e2
  
  Small changes to make the US weather dataset work properly, example test runs in config file. master Kevin Alberts 2021-01-29 10:52:49 +0100
• e4c51e2d3d
  
  Allow loss function to be defined by the dataset. Add specialized loss function for US weather dataset Kevin Alberts 2021-01-21 21:47:00 +0100
• f6a19c4921
  
  Allow input shape to be defined by dataset, save loss values as csv after training, implemented basic version of US weather dataset, but it is very slow and has bad results probably due to input encoding issue Kevin Alberts 2021-01-20 21:48:31 +0100
• f76374111c
  
  Add mssim score calculation, corrupt test data before testing, clip noise to avoid invalid values Kevin Alberts 2021-01-17 16:59:14 +0100
• bc95548ae3
  
  Move saving of samples to dataset, as the process differs per dataset. Add MNIST dataset. Allow saving labels with the dataset (for use in tabular data in the future) Kevin Alberts 2021-01-14 18:45:26 +0100
• fb9ce46bd8
  
  Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations - Encoders: sparse, denoising, contractive and variational - Noise: gaussian Kevin Alberts 2020-12-29 18:44:44 +0100
• 62f9b873e9
  
  First basic auto-encoder and CIFAR-10 dataset implemented Kevin Alberts 2020-12-28 13:09:18 +0100
• 51cc5d1d30
  
  Initial, very basic framework for running comparison tests Kevin Alberts 2020-11-24 17:19:46 +0100