Kevin Alberts 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		2021-01-20 21:48:31 +01:00
..
__init__.py	Initial, very basic framework for running comparison tests	2020-11-24 17:19:46 +01:00
base_corruption.py	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	2021-01-20 21:48:31 +01:00
base_dataset.py	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	2021-01-20 21:48:31 +01:00
base_encoder.py	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	2021-01-20 21:48:31 +01:00
basic_encoder.py	Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations	2020-12-29 18:44:44 +01:00
cifar10_dataset.py	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	2021-01-20 21:48:31 +01:00
contractive_encoder.py	Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations	2020-12-29 18:44:44 +01:00
denoising_encoder.py	Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations	2020-12-29 18:44:44 +01:00
gaussian_corruption.py	Add mssim score calculation, corrupt test data before testing, clip noise to avoid invalid values	2021-01-17 16:59:14 +01:00
mnist_dataset.py	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	2021-01-20 21:48:31 +01:00
random_corruption.py	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	2021-01-20 21:48:31 +01:00
sparse_encoder.py	Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations	2020-12-29 18:44:44 +01:00
test_run.py	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	2021-01-20 21:48:31 +01:00
usweather_dataset.py	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	2021-01-20 21:48:31 +01:00
variational_encoder.py	Implement types of auto-encoders and corruption, use log scale in loss graphs, lots of helper function hooks in training process to allow implementations	2020-12-29 18:44:44 +01:00