mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-27 14:39:43 +00:00
pepijn
3fdfcb912a
- Add ATOMIC_TASKS, COMPOSITE_UNSEEN_TASKS and four new --task-set keys (atomic, composite_unseen, composite_all, composite_atomic) so the same builder produces the 50-task target benchmark or the 300-task Human300 pretraining slice (via --split=pretrain --task-set=all) without duplicating logic. - Stop hardcoding the composite_seen tag on the HF push; tags are now derived from --split / --source / --task-set so atomic, composite_all, and pretrain runs land with accurate metadata. - Refresh module docstring to match the broader scope. - Add scripts/build_robocasa_smoke.sh: 2-atomic-task smoke dataset (~1k episodes, ~131k frames) for fast end-to-end training validation before kicking off Human300-scale runs.
48 lines
1.4 KiB
Bash
Executable File
48 lines
1.4 KiB
Bash
Executable File
#!/bin/bash
|
|
# Build a tiny RoboCasa smoke dataset (2 short atomic tasks, all episodes) for
|
|
# fast end-to-end training validation before the real run.
|
|
#
|
|
# Defaults: target/human, OpenStandMixerHead + NavigateKitchen (~1k episodes,
|
|
# ~131k frames, ~109 min @ 20 fps), 2 SLURM workers on hopper-cpu.
|
|
#
|
|
# Override via env: TASKS, REPO_ID, WORK_DIR, WORKERS, CPUS, PARTITION, LOCAL=1.
|
|
|
|
set -euo pipefail
|
|
|
|
cd "${LEROBOT_ROOT:-$HOME/lerobot}"
|
|
source ~/miniconda3/etc/profile.d/conda.sh
|
|
conda activate lerobot
|
|
|
|
REPO_ID="${REPO_ID:-${HF_USER:?HF_USER is unset}/robocasa_smoke_2atomic_v3}"
|
|
WORK_DIR="${WORK_DIR:-/fsx/${USER}/robocasa/datasets/v1.0}"
|
|
ROBOCASA_ROOT="${ROBOCASA_ROOT:-/fsx/${USER}/robocasa}"
|
|
LOGS_DIR="${LOGS_DIR:-/fsx/${USER}/logs/robocasa}"
|
|
TASKS="${TASKS:-OpenStandMixerHead NavigateKitchen}"
|
|
WORKERS="${WORKERS:-2}"
|
|
CPUS="${CPUS:-8}"
|
|
PARTITION="${PARTITION:-hopper-cpu}"
|
|
LOCAL="${LOCAL:-0}"
|
|
|
|
ARGS=(
|
|
examples/port_datasets/slurm_build_robocasa_composite_seen.py
|
|
--repo-id="$REPO_ID"
|
|
--work-dir="$WORK_DIR"
|
|
--robocasa-root="$ROBOCASA_ROOT"
|
|
--split=target --source=human
|
|
--tasks $TASKS
|
|
--workers="$WORKERS"
|
|
--cpus-per-task="$CPUS"
|
|
--partition="$PARTITION"
|
|
--mem-per-cpu=4G
|
|
--time=04:00:00
|
|
--logs-dir="$LOGS_DIR"
|
|
--job-name=port_robocasa_smoke
|
|
)
|
|
if [[ "$LOCAL" == "1" ]]; then
|
|
ARGS+=(--slurm=0)
|
|
fi
|
|
|
|
echo "Smoke dataset: $REPO_ID"
|
|
echo "Tasks: $TASKS"
|
|
python "${ARGS[@]}"
|