mirror of
https://github.com/nerfstudio-project/nerfstudio.git
synced 2026-11-19 22:25:44 +08:00
Add Docker build/run environment and simplify README for release
- Dockerfile: build the full PanDORA env on CUDA 11.7 (torch 2.0.1+cu117, pinned via a global PIP_CONSTRAINT so nothing upgrades torch to a driver-incompatible CUDA build), tiny-cuda-nn v1.6, pyequilib 0.5.6, numpy<2, viser 0.0.16, and Blender. Removes the unused COLMAP/SfM stack, caps compile parallelism (MAKE_JOBS), and sets PYTHONPATH for lantern_scripts. - docker/build_and_run.sh: build the image (tunable CUDA_VERSION/MAKE_JOBS) and run the pipeline or an interactive GPU shell, mounting the repo + data. - docker/run_pandora_pipeline.sh: fixed two-stage PanDORA training pipeline. - docker/download_scenes.sh: download PanDORA dataset scenes by name. - README.md: rewrite as a simple 4-step Docker quick start; point advanced users to README-pandora.md / README-hdrnerfacto.md. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
1 parent
287f56176b
commit
0197bd32ed
5 files changed
+480
-357
No files matched your search
@@ -0,0 +1,86 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Build the PanDORA docker image and run the fixed two-stage training pipeline
|
||||
# inside it, with GPU access and the repo + dataset mounted at runtime.
|
||||
#
|
||||
# Usage:
|
||||
# docker/build_and_run.sh [--rebuild] [--shell]
|
||||
#
|
||||
# --rebuild Rebuild the image from scratch (docker build --no-cache).
|
||||
# --shell Drop into an interactive shell instead of running the pipeline.
|
||||
#
|
||||
# Common environment overrides:
|
||||
# DATA_ROOT Host dir mounted to /data (default below)
|
||||
# DATASET_DIR Container path to a *_ns scene (default below, under /data)
|
||||
# STEP1_ITERS / STEP2_ITERS Lower for a quick smoke test.
|
||||
set -euo pipefail
|
||||
|
||||
# --- Configuration -----------------------------------------------------------
|
||||
IMAGE="${IMAGE:-pandora:latest}"
|
||||
# Repo root = parent of this script's directory.
|
||||
REPO="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
# Host data directory that holds the processed scenes; mounted to /data.
|
||||
DATA_ROOT="${DATA_ROOT:-/home-local2/${USER}.extra.nobkp/nerfstudio_ds}"
|
||||
# Container-side path to the scene to train on (lives under /data).
|
||||
DATASET_DIR="${DATASET_DIR:-/data/sample_scene/sample_scene_ns/}"
|
||||
SHM_SIZE="${SHM_SIZE:-12gb}"
|
||||
|
||||
REBUILD=0
|
||||
RUN_SHELL=0
|
||||
for arg in "$@"; do
|
||||
case "$arg" in
|
||||
--rebuild) REBUILD=1 ;;
|
||||
--shell) RUN_SHELL=1 ;;
|
||||
-h|--help)
|
||||
sed -n '2,20p' "${BASH_SOURCE[0]}" | sed 's/^# \{0,1\}//'
|
||||
exit 0 ;;
|
||||
*) echo "Unknown argument: $arg" >&2; exit 1 ;;
|
||||
esac
|
||||
done
|
||||
|
||||
# --- Build -------------------------------------------------------------------
|
||||
# Parallel compile jobs for the from-source builds (ceres/colmap/tcnn). Keep
|
||||
# modest to avoid GCC OOM/segfault on the heavy Ceres template files; raise on
|
||||
# high-RAM machines, e.g. MAKE_JOBS=8 docker/build_and_run.sh.
|
||||
MAKE_JOBS="${MAKE_JOBS:-4}"
|
||||
# CUDA toolkit version for the base image + torch/tcnn build. Must be <= the max
|
||||
# CUDA version your host NVIDIA driver supports (see `nvidia-smi`). Default 11.7.1
|
||||
# (torch 2.0.1+cu117) matches the known-working env and runs on older drivers
|
||||
# (r450+). torch 2.0.1 also ships cu118 wheels if your driver is newer.
|
||||
CUDA_VERSION="${CUDA_VERSION:-11.7.1}"
|
||||
BUILD_ARGS=(-t "$IMAGE" -f "$REPO/Dockerfile"
|
||||
--build-arg MAKE_JOBS="$MAKE_JOBS"
|
||||
--build-arg CUDA_VERSION="$CUDA_VERSION"
|
||||
"$REPO")
|
||||
if [ "$REBUILD" -eq 1 ]; then
|
||||
echo ">> Rebuilding image '$IMAGE' from scratch (--no-cache)..."
|
||||
docker build --no-cache "${BUILD_ARGS[@]}"
|
||||
else
|
||||
echo ">> Building image '$IMAGE' (cached)..."
|
||||
docker build "${BUILD_ARGS[@]}"
|
||||
fi
|
||||
|
||||
# --- Run ---------------------------------------------------------------------
|
||||
# Mount the repo onto the same path the image installed it editable (-e .), so
|
||||
# the live code is used and the editable install stays valid.
|
||||
DOCKER_RUN=(
|
||||
docker run --rm -it
|
||||
--gpus all
|
||||
--shm-size="$SHM_SIZE"
|
||||
-v "$REPO":/home/user/nerfstudio
|
||||
-v "$DATA_ROOT":/data
|
||||
-e DATASET_DIR="$DATASET_DIR"
|
||||
-e EXPERIMENT_NAME="${EXPERIMENT_NAME:-pandora}"
|
||||
-e STEP1_ITERS="${STEP1_ITERS:-60000}"
|
||||
-e STEP2_ITERS="${STEP2_ITERS:-120000}"
|
||||
-w /home/user/nerfstudio
|
||||
"$IMAGE"
|
||||
)
|
||||
|
||||
if [ "$RUN_SHELL" -eq 1 ]; then
|
||||
echo ">> Launching interactive shell in '$IMAGE'..."
|
||||
exec "${DOCKER_RUN[@]}" bash
|
||||
else
|
||||
echo ">> Running PanDORA pipeline in '$IMAGE' on DATASET_DIR=$DATASET_DIR ..."
|
||||
exec "${DOCKER_RUN[@]}" bash docker/run_pandora_pipeline.sh
|
||||
fi
|
||||
@@ -0,0 +1,132 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Download PanDORA dataset scenes by name.
|
||||
# Scenes are hosted as individual ZIP archives (~5 GB each) at:
|
||||
# https://hdrdb-public.s3.valeria.science/pandora/<scene>.zip
|
||||
# See: https://lvsn.github.io/pandora/dataset/index.html
|
||||
#
|
||||
# Usage:
|
||||
# docker/download_scenes.sh <scene> [<scene> ...]
|
||||
# docker/download_scenes.sh all
|
||||
# docker/download_scenes.sh --list
|
||||
#
|
||||
# Options:
|
||||
# --dest DIR Destination directory (default: $DATA_ROOT or /data)
|
||||
# --keep-zip Keep the downloaded .zip after extracting (default: delete)
|
||||
# --force Re-download / re-extract even if already present
|
||||
# --list Print the available scene names and exit
|
||||
#
|
||||
# Downloads are resumable (curl -C -), so re-running continues an interrupted
|
||||
# download. Extraction is skipped if the scene is already present unless --force.
|
||||
set -euo pipefail
|
||||
|
||||
BASE_URL="https://hdrdb-public.s3.valeria.science/pandora"
|
||||
|
||||
# The 14 available scenes (exact zip basenames).
|
||||
SCENES=(
|
||||
auditorium
|
||||
auditorium_dark
|
||||
basement
|
||||
blue_bedroom
|
||||
classroom_no_windows
|
||||
classroom_windows
|
||||
clubhouse
|
||||
coffee_room
|
||||
lab_office
|
||||
living_room
|
||||
lobby
|
||||
meeting_room
|
||||
office
|
||||
small_office
|
||||
)
|
||||
|
||||
DEST="${DATA_ROOT:-/data}"
|
||||
KEEP_ZIP=0
|
||||
FORCE=0
|
||||
REQUESTED=()
|
||||
|
||||
is_valid_scene() {
|
||||
local s="$1"
|
||||
for known in "${SCENES[@]}"; do
|
||||
[ "$known" = "$s" ] && return 0
|
||||
done
|
||||
return 1
|
||||
}
|
||||
|
||||
print_list() {
|
||||
echo "Available PanDORA scenes (${#SCENES[@]}):"
|
||||
for s in "${SCENES[@]}"; do echo " - $s"; done
|
||||
}
|
||||
|
||||
# --- Parse arguments ---------------------------------------------------------
|
||||
while [ $# -gt 0 ]; do
|
||||
case "$1" in
|
||||
--dest) DEST="$2"; shift 2 ;;
|
||||
--keep-zip) KEEP_ZIP=1; shift ;;
|
||||
--force) FORCE=1; shift ;;
|
||||
--list) print_list; exit 0 ;;
|
||||
-h|--help) sed -n '2,25p' "${BASH_SOURCE[0]}" | sed 's/^# \{0,1\}//'; exit 0 ;;
|
||||
all) REQUESTED=("${SCENES[@]}"); shift ;;
|
||||
-*) echo "Unknown option: $1" >&2; exit 1 ;;
|
||||
*) REQUESTED+=("$1"); shift ;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [ ${#REQUESTED[@]} -eq 0 ]; then
|
||||
echo "ERROR: no scene(s) specified." >&2
|
||||
echo >&2
|
||||
print_list >&2
|
||||
echo >&2
|
||||
echo "Example: docker/download_scenes.sh meeting_room coffee_room" >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate all requested names up front.
|
||||
for s in "${REQUESTED[@]}"; do
|
||||
if ! is_valid_scene "$s"; then
|
||||
echo "ERROR: unknown scene '$s'." >&2
|
||||
echo >&2
|
||||
print_list >&2
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
|
||||
mkdir -p "$DEST"
|
||||
|
||||
# --- Download + extract ------------------------------------------------------
|
||||
for scene in "${REQUESTED[@]}"; do
|
||||
marker="$DEST/.$scene.done"
|
||||
zip="$DEST/$scene.zip"
|
||||
url="$BASE_URL/$scene.zip"
|
||||
|
||||
echo "=================================================================="
|
||||
echo "Scene: $scene"
|
||||
echo " URL : $url"
|
||||
echo " Dest: $DEST"
|
||||
echo "=================================================================="
|
||||
|
||||
if [ -f "$marker" ] && [ "$FORCE" -eq 0 ]; then
|
||||
echo "Already downloaded and extracted (marker $marker exists); skipping."
|
||||
echo "Use --force to re-download."
|
||||
continue
|
||||
fi
|
||||
|
||||
echo "Downloading (resumable)..."
|
||||
curl -L -f --retry 5 --retry-delay 5 -C - -o "$zip" "$url"
|
||||
|
||||
echo "Extracting..."
|
||||
unzip -q -o "$zip" -d "$DEST"
|
||||
|
||||
touch "$marker"
|
||||
|
||||
if [ "$KEEP_ZIP" -eq 0 ]; then
|
||||
echo "Removing archive $zip (use --keep-zip to keep)..."
|
||||
rm -f "$zip"
|
||||
fi
|
||||
|
||||
echo "Done: $scene"
|
||||
done
|
||||
|
||||
echo "=================================================================="
|
||||
echo "All requested scenes are ready under: $DEST"
|
||||
echo "=================================================================="
|
||||
@@ -0,0 +1,80 @@
|
||||
#!/usr/bin/env bash
|
||||
#
|
||||
# Fixed PanDORA two-stage training pipeline (README "Option A").
|
||||
# Runs inside the PanDORA docker image, but also works in an interactive shell.
|
||||
#
|
||||
# step 1 (lantern_steps 1) -> align_fast_to_well.py -> step 2 (lantern_steps 2)
|
||||
#
|
||||
# The dataset is provided via the DATASET_DIR env var (a processed *_ns scene).
|
||||
# Deterministic --experiment-name / --timestamp make the step-1 outputs a known
|
||||
# path that the align + step-2 commands can reference.
|
||||
set -euo pipefail
|
||||
|
||||
# Make the repo root importable so `lantern_scripts` (used by nerfstudio's lantern
|
||||
# processors/config) resolves even if PYTHONPATH isn't already set in the env.
|
||||
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
|
||||
export PYTHONPATH="${REPO_ROOT}:${PYTHONPATH:-}"
|
||||
|
||||
# --- Configuration (override via environment) --------------------------------
|
||||
# Processed nerfstudio scene directory (contains transforms.json, images/, ...).
|
||||
DATASET_DIR="${DATASET_DIR:-/data/sample_scene/sample_scene_ns/}"
|
||||
EXPERIMENT_NAME="${EXPERIMENT_NAME:-pandora}"
|
||||
# Iteration counts (lower these for a quick smoke test, e.g. STEP1_ITERS=200).
|
||||
STEP1_ITERS="${STEP1_ITERS:-60000}"
|
||||
STEP2_ITERS="${STEP2_ITERS:-120000}"
|
||||
NUM_IMAGES_TO_SAMPLE="${NUM_IMAGES_TO_SAMPLE:-1800}"
|
||||
|
||||
STEP1_OUT="outputs/${EXPERIMENT_NAME}/PanDORA/step_1"
|
||||
STEP2_OUT="outputs/${EXPERIMENT_NAME}/PanDORA/step_2"
|
||||
|
||||
if [ ! -d "$DATASET_DIR" ]; then
|
||||
echo "ERROR: DATASET_DIR does not exist: $DATASET_DIR"
|
||||
echo "Set DATASET_DIR to a processed nerfstudio scene (a *_ns directory)."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "=================================================================="
|
||||
echo "PanDORA two-stage training"
|
||||
echo " DATASET_DIR = $DATASET_DIR"
|
||||
echo " EXPERIMENT_NAME = $EXPERIMENT_NAME"
|
||||
echo " step 1 iters = $STEP1_ITERS -> $STEP1_OUT"
|
||||
echo " step 2 iters = $STEP2_ITERS -> $STEP2_OUT"
|
||||
echo "=================================================================="
|
||||
|
||||
# --- Step 1: train on two exposures (lantern step 1) -------------------------
|
||||
echo "[1/3] Training PanDORA step 1..."
|
||||
ns-train PanDORA \
|
||||
--data "$DATASET_DIR" \
|
||||
--experiment-name "$EXPERIMENT_NAME" \
|
||||
--timestamp step_1 \
|
||||
--output-dir outputs \
|
||||
--pipeline.datamanager.train-num-images-to-sample-from "$NUM_IMAGES_TO_SAMPLE" \
|
||||
--pipeline.model.lantern_steps 1 \
|
||||
--pipeline.datamanager.pixel-sampler.lantern_steps 1 \
|
||||
--max-num-iterations "$STEP1_ITERS" \
|
||||
--viewer.quit-on-train-completion True
|
||||
|
||||
# --- Step 2a: align fast exposure to well exposure ---------------------------
|
||||
echo "[2/3] Aligning fast exposure to well exposure..."
|
||||
python lantern_scripts/align_fast_to_well.py \
|
||||
--input_dir "$DATASET_DIR" \
|
||||
--config "$STEP1_OUT/config.yml"
|
||||
|
||||
# --- Step 2b: train on aligned two exposures (lantern step 2) ----------------
|
||||
echo "[3/3] Training PanDORA step 2..."
|
||||
ns-train PanDORA \
|
||||
--data "$DATASET_DIR" \
|
||||
--experiment-name "$EXPERIMENT_NAME" \
|
||||
--timestamp step_2 \
|
||||
--output-dir outputs \
|
||||
--pipeline.datamanager.train-num-images-to-sample-from "$NUM_IMAGES_TO_SAMPLE" \
|
||||
--pipeline.model.lantern_steps 2 \
|
||||
--pipeline.datamanager.pixel-sampler.lantern_steps 2 \
|
||||
--pipeline.model.apply_mu_law False \
|
||||
--load-dir "$STEP1_OUT/nerfstudio_models" \
|
||||
--max-num-iterations "$STEP2_ITERS" \
|
||||
--viewer.quit-on-train-completion True
|
||||
|
||||
echo "=================================================================="
|
||||
echo "Done. Final model: $STEP2_OUT"
|
||||
echo "=================================================================="
|
||||
Reference in new issue
Block a user