ran hyperparameter search wfor cnn with relu and batchnorm

add simple conv model with relu and batchnorm

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

add non-pretrained-focus-liteNN model

add hyperparameter optimisation runs for resnet

add hyperparameter optimisation run that did not finish

rerun and add logs for focusResNet101_pretrained_150

rerun and add logs for focusResNet_150

rerun and add logs for focusMSE_150

rerun and add logs for focusMAE_150

rerun and add logs for focusConvMSE_besthyp_150

rerun and add logs for focusConvMSE_150

remove old runs to rerun all experiments

add training opimization results for simple cnn

add results of simple cnn benchmark

add hyperparameter optimisation run

add runs for first experiments

remove all runs due to results being not useful (error in loss function)

remove all checkpoint files from earlier runs

ignore .chpt files

run experiments comparing MSE and MAE

add hyperparameter tuning experiment with more data for focus

add so far done experiments