Try a loss function that has higher values for errors near sea level

Dependencies

• [2] 7ML3OFE7 Model trainer: initial train and visualize thread pair (total crust mass; todo: altitude instead)
• [3] SJHJS463 Model trainer: main function to open sdl window and launch second thread for actual training
• [4] CWOSQTC4 Trust tensorflow's thread safety (it wasn't the cause of an earlier bug)
• [*] ZM2EMAZO Start doing python multi-module stuff properly

Change contents

• edit in trainmodel/src/model.py at line 28
  [2.1746]

  [2.1746]
  + def shore_focused_loss(y_true, y_pred):

  + y_true = tf.math.asinh(y_true - 4.94e-4)

  + y_pred = tf.math.asinh(y_pred - 4.94e-4)

  + return tf.math.reduce_mean((y_true - y_pred) ** 2)

  +
• replacement in trainmodel/src/__main__.py at line 26
  [2.327]→[2.327:376](∅→∅)
  − loss=keras.losses.MeanSquaredError()
  [2.327]

  [2.376]
  + loss=model.shore_focused_loss