ran hyperparameter search wfor cnn with relu and batchnorm

add simple conv model with relu and batchnorm

replotted speed graph

add folder to docker ignore

rerun all relevant notebooks

add models to presented models to make it easier to find them

run fc models hyperparameter tuning again on MSE model

add optimization run for cnn

Revert "change conv model to use activation function and rerun a training run" as it degrades performance

run experiments with relu in cnn

change conv model to use activation function and rerun a training run

regenerate all plots and make sure they all contain the proper model names

rerun notebooks after changing mdct

fix mdct (add square)

add violing plots

update names in figure to resemble in thesis

create pdf with speed measures

add speed comparison

change measurements to only measure computation time not transfer time

add non-pretrained-focus-liteNN model

add speed benchmarks

fix vol4 function

improve tables

update notebooks to use different resnet101 model

add comparison of models to notebooks

add mean laplacian and mdct

add traditional method for comparison

add code for vol4 implementation

update file to use current best model and add speedtest for different model sizes

add hyperparameter optimisation runs for resnet

remove error causeing (?) ResNET parameter and reduce range of lr

add hyperparameter optimisation run that did not finish

improve contour plot to be more legible

add stiched image

improve legend for heatmap

fix notebook to properly load data again

regenerate images to fix wrong legend

add plot to visualise results

add pdf and ipynb to git lfs

improve plotting of heatmaps and results

fix error in resnet code, don*t run constructor in place

add image stiching to exploration notebook

add notebook to be able to evaluate more models

add better contour plot using argmin and abs

add contour images to notebook

add drawing heatmap of example focus stack

add gpu support to notebook

add example images to notebook

rerun notebook with latest model

rerun and add logs for focusResNet101_pretrained_150