143a837c03
- Add scripts/run_gta_uav.py for GTA-UAV-LR (48K images, GTA V synthetic) - 14 segmentation classes: 11 base + bare soil, rooftop, swimming pool - Fix source filter to recognize "satellite" folder (alongside "DB") - Document GTA-UAV characteristics in segmentation_class_analysis.md - Update README and CLAUDE.md with GTA-UAV support Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
117 lines
3.6 KiB
Python
117 lines
3.6 KiB
Python
#!/usr/bin/env python3
|
|
"""Run annotation pipeline for GTA-UAV-LR dataset.
|
|
|
|
GTA-UAV-LR: synthetic dataset from GTA V engine.
|
|
- drone/images/: 33763 images, 512x384, RGB PNG
|
|
- satellite/: 14640 images, 256x256, RGBA PNG (alpha = map boundary)
|
|
- Total: 48403 images
|
|
- 6 flight heights: 100, 200, 300, 400, 500, 600 meters
|
|
|
|
Usage:
|
|
python scripts/run_gta_uav.py
|
|
python scripts/run_gta_uav.py --source db # only satellite (14.6K)
|
|
python scripts/run_gta_uav.py --source drone # only drone (33.8K)
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
_PROJECT_ROOT = Path(__file__).resolve().parent.parent
|
|
sys.path.insert(0, str(_PROJECT_ROOT))
|
|
|
|
import numpy as np
|
|
import torch
|
|
|
|
from src.conf.hardware_conf import HardwareConfig
|
|
from src.conf.input_conf import InputConfig
|
|
from src.conf.models_conf import ModelsConfig
|
|
from src.conf.pipeline_conf import PipelineConfig
|
|
from src.conf.seg_conf import SegConfig
|
|
from src.augmentor.io_utils import setup_logging
|
|
from src.main import run_pipeline
|
|
|
|
|
|
INPUT_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR"
|
|
OUTPUT_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR-aug"
|
|
|
|
|
|
def main() -> None:
|
|
parser = argparse.ArgumentParser(description="Annotate GTA-UAV-LR")
|
|
parser.add_argument("--source", choices=["db", "drone", "all"], default="all",
|
|
help="Process only db (satellite), drone, or all (default)")
|
|
parser.add_argument("--stages", nargs="+",
|
|
default=["depth", "edges", "segmentation", "chmv2"],
|
|
help="Stages to run")
|
|
args = parser.parse_args()
|
|
|
|
import gin
|
|
gin.clear_config()
|
|
|
|
source = None if args.source == "all" else args.source
|
|
if source == "drone":
|
|
source = "query"
|
|
|
|
pipeline_conf = PipelineConfig(
|
|
input_root=INPUT_ROOT,
|
|
output_root=OUTPUT_ROOT,
|
|
stages=args.stages,
|
|
save_npy=False,
|
|
save_vis=True,
|
|
save_safetensors=True,
|
|
cleanup_npy=True,
|
|
resume=True,
|
|
source=source,
|
|
log_level="INFO",
|
|
)
|
|
|
|
hw_conf = HardwareConfig(
|
|
profile_name="rtx4090",
|
|
total_ram_gb=24.0,
|
|
reserve_gb=2.0,
|
|
use_fp16=True,
|
|
batch_size=None,
|
|
num_workers=4,
|
|
)
|
|
|
|
# GTA-UAV: satellite 256x256, drone 512x384
|
|
# Use 256 for satellite, 512 for drone (non-square → resize to square)
|
|
input_conf = InputConfig(image_size=256, query_image_size=512)
|
|
|
|
# GTA V synthetic scenes: urban, suburban, rural, coastal, mountainous
|
|
# 11 base classes + pool (swimming pools common in GTA suburbs)
|
|
seg_conf = SegConfig(threshold=0.15, prompts=[
|
|
"background", # 0
|
|
"building", # 1
|
|
"road", # 2
|
|
"vegetation", # 3
|
|
"water", # 4
|
|
"sand and gravel ground", # 5
|
|
"rocky terrain", # 6
|
|
"farmland", # 7
|
|
"railway", # 8
|
|
"parking lot", # 9
|
|
"sidewalk", # 10
|
|
"bare soil and plowed field", # 11
|
|
"roof and rooftop", # 12
|
|
"swimming pool", # 13
|
|
])
|
|
|
|
models_conf = ModelsConfig(weights_dir=str(_PROJECT_ROOT / "in" / "weights"))
|
|
|
|
setup_logging(
|
|
pipeline_conf.log_level,
|
|
log_file=Path(OUTPUT_ROOT) / "pipeline.log",
|
|
)
|
|
|
|
torch.manual_seed(42)
|
|
np.random.seed(42)
|
|
|
|
run_pipeline(pipeline_conf, hw_conf, models_conf, input_conf, seg_conf)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|