feat: first training attempt

It still sucks. I'm sure the the feature embedding is terribly wrong.
2026-07-29 22:25:15 +02:00
parent c31507a2cb
commit dcb46ec908
5 changed files with 476 additions and 3 deletions
@@ -0,0 +1,88 @@
+#!/usr/bin/env bash
+
+set -euo pipefail
+
+ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+DATA_DIR="${ROOT_DIR}/data"
+OUTPUT_FILE="${ROOT_DIR}/sleep-model.pt"
+MODEL_FILE="${OUTPUT_FILE}"
+
+if [[ ${1:-} == "-h" || ${1:-} == "--help" ]]; then
+  cat <<'EOF'
+Usage: scripts/train_from_data.sh [-o OUTPUT_FILE]
+
+Trains the model on complete session triplets found under data/{motion,heart_rate,labels}/.
+EOF
+  exit 0
+fi
+
+if [[ ${1:-} == "-o" || ${1:-} == "--output" ]]; then
+  OUTPUT_FILE="${2:?Missing output file after -o/--output}"
+  MODEL_FILE="${OUTPUT_FILE}"
+fi
+
+shopt -s nullglob
+
+checkpoint_class_count() {
+  python - "$1" <<'PY'
+from pathlib import Path
+import sys
+import torch
+
+payload = torch.load(Path(sys.argv[1]), weights_only=True)
+state_dict = payload.get("model_state_dict", payload)
+print(state_dict["net.2.bias"].shape[0])
+PY
+}
+
+motions=("${DATA_DIR}/motion"/*_acceleration.txt)
+
+subject_ids=()
+
+for motion_file in "${motions[@]}"; do
+  sample_id="$(basename "${motion_file}" _acceleration.txt)"
+  heartrate_file="${DATA_DIR}/heart_rate/${sample_id}_heartrate.txt"
+  label_file="${DATA_DIR}/labels/${sample_id}_labeled_sleep.txt"
+
+  if [[ -f "${heartrate_file}" && -f "${label_file}" ]]; then
+    subject_ids+=("${sample_id}")
+  fi
+done
+
+if [[ ${#subject_ids[@]} -eq 0 ]]; then
+  printf 'No complete data triplets found under %s\n' "${DATA_DIR}" >&2
+  exit 1
+fi
+
+mapfile -t subject_ids < <(printf '%s\n' "${subject_ids[@]}" | sort -u)
+
+printf 'Training on %d subject(s)\n' "${#subject_ids[@]}"
+
+export PYTHONPATH="${ROOT_DIR}/src${PYTHONPATH:+:${PYTHONPATH}}"
+
+for subject_id in "${subject_ids[@]}"; do
+  acceleration_file="${DATA_DIR}/motion/${subject_id}_acceleration.txt"
+  heartrate_file="${DATA_DIR}/heart_rate/${subject_id}_heartrate.txt"
+  label_file="${DATA_DIR}/labels/${subject_id}_labeled_sleep.txt"
+  resume_args=()
+
+  printf 'Training subject %s\n' "${subject_id}"
+
+  if [[ -f "${MODEL_FILE}" ]]; then
+    checkpoint_classes="$(checkpoint_class_count "${MODEL_FILE}")"
+    if [[ "${checkpoint_classes}" == "3" ]]; then
+      resume_args=(-i "${MODEL_FILE}")
+    else
+      printf 'Skipping checkpoint for subject %s: model classes=%s, expected=3\n' "${subject_id}" "${checkpoint_classes}"
+    fi
+  fi
+
+  args=(python -m sleep_detection train -a "${acceleration_file}" -H "${heartrate_file}" -l "${label_file}" -o "${MODEL_FILE}")
+  if [[ ${#resume_args[@]} -gt 0 ]]; then
+    args+=("${resume_args[@]}")
+  fi
+
+  "${args[@]}"
+done
+
+printf 'Saved trained model to %s\n' "${MODEL_FILE}"