research-rainfallradar/aimodel/slurm-encoderonly-rainfall.job
2023-02-10 13:28:34 +00:00

80 lines
4.2 KiB
Bash
Executable file
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

#!/usr/bin/env bash
#SBATCH -J EncORain
#SBATCH -N 1
#SBATCH -n 14
#SBATCH --gres=gpu:1
#SBATCH -o %j.%N.%a.encoderonly-rainfall.out.log
#SBATCH -e %j.%N.%a.encoderonly-rainfall.err.log
#SBATCH -p gpu
#SBATCH --no-requeue
#SBATCH --time=5-00:00:00
#SBATCH --mem=30000
# ---> in MiB
# no-requeue: ref https://support.hull.ac.uk/tas/public/ssp/content/detail/incident?unid=652db7ac6e73485c9f7658db78b2b628
module load utilities/multi
module load readline/7.0
module load gcc/10.2.0
module load cuda/11.5.0
export XLA_FLAGS="--xla_gpu_cuda_data_dir=/home/ViperAppsFiles/cuda/11.5.0"; # weird... this wasn't needed before?
module load python/anaconda/4.6/miniconda/3.7
show_help() {
echo -e "Trains a TEST encoderonly model using rainfall radar and water depth data." >&2;
echo -e "" >&2;
echo -e "Usage:" >&2;
echo -e " sbatch slurm-encoderonly-rainfall.job" >&2;
echo -e "" >&2;
echo -e "....where:" >&2;
echo -e " BATCH_SIZE=64 Optional. Sets the batch size to train the model with." >&2;
echo -e " DIRPATH_RAINFALLWATER The path to the directory the .tfrecord files containing the rainfall radar / water depth data." >&2;
echo -e " PATH_HEIGHTMAP The path to the heightmap jsonl file to read in." >&2;
# echo -e " PATH_COLOURMAP The path to the colourmap for predictive purposes." >&2;
echo -e " CHANNELS=8 The number of channels the input data has." >&2;
echo -e " WINDOW_SIZE=33 The window size to use when convolving the input dataset for single pixel prediction." >&2;
echo -e " STEPS_PER_EPOCH The number of steps to consider an epoch. Defaults to None, which means use the entire dataset." >&2;
echo -e " VAL_STEPS_PER_EPOCH The number of validation steps to consider an epoch. Defaults to None, which means use the entire dataset." >&2;
echo -e " STEPS_PER_EXECUTION The number of steps to do before returning to do callbacks. High numbers boost performance. Defaults to 1. If set then STEPS_PER_EPOCH and VAL_STEPS_PER_EPOCH must also be set." >&2;
echo -e " EPOCHS=25 The number of epochs to train for." >&2;
echo -e " LEARNING_RATE The learning rate to use. Default: 0.001." >&2;
# echo -e " NO_REMOVE_ISOLATED_PIXELS Set to any value to avoid the engine from removing isolated pixels - that is, water pixels with no other surrounding pixels, either side to side to diagonally." >&2;
# echo -e " PATH_CHECKPOINT The path to a checkcpoint to load. If specified, a model will be loaded instead of being trained." >&2;
# echo -e " PREDICT_COUNT The number of items from the (SCRAMBLED) dataset to make a prediction for." >&2;
echo -e " POSTFIX Postfix to append to the output dir (auto calculated)." >&2;
echo -e " ARGS Optional. Any additional arguments to pass to the python program." >&2;
echo -e "" >&2;
echo -e "It is strongly advised that all filepaths do NOT contain spaces." >&2;
exit;
}
DIRPATH_RAINFALLWATER="${DIRPATH_RAINFALLWATER:-$HOME/rainfallwater_records_tfrecord}";
PATH_HEIGHTMAP="${PATH_HEIGHTMAP:-$HOME/data/terrain50-nimrodsized.json.gz}";
PATH_COLOURMAP="${PATH_COLOURMAP:-$HOME/data/instance-level-human-parsing/instance-level_human_parsing/human_colormap.mat}";
CODE="encoderonly_rainfall";
if [[ -n "${POSTFIX}" ]]; then
echo -e ">>> Applying postfix of ${POSTFIX}" >&2;
CODE="${CODE}_${POSTFIX}";
fi
DIRPATH_OUTPUT="output/$(date -u --rfc-3339=date)_${CODE}";
mkdir -p "${DIRPATH_OUTPUT}";
echo -e ">>> NOW: $(date)";
echo -e ">>> DIR_OUTPUT: ${DIR_OUTPUT}";
echo -e ">>> Additional args: ${ARGS}";
export PATH=$HOME/software/bin:$PATH;
export BATCH_SIZE DIRPATH_RAINFALLWATER PATH_HEIGHTMAP STEPS_PER_EPOCH VAL_STEPS_PER_EPOCH DIRPATH_OUTPUT PATH_CHECKPOINT CHANNELS WINDOW_SIZE EPOCHS LEARNING_RATE STEPS_PER_EXECUTION;
#LOSS ;
echo ">>> Installing requirements";
conda run -n py38 pip install -q -r requirements.txt;
echo ">>> Training model";
#shellcheck disable=SC2016
/usr/bin/env time -v conda run -n py38 bash -c 'src/encoderonly_test_rainfall.py >>"${DIRPATH_OUTPUT}/experiment.${SLURM_JOB_ID}.out.log" 2>>"${DIRPATH_OUTPUT}/experiment.${SLURM_JOB_ID}.err.log"; echo "[slurm_runner] EXIT_CODE: $?" >>"${DIRPATH_OUTPUT}/experiment.${SLURM_JOB_ID}.out.log";';
echo ">>> exited with code $?";