Spaces:
Running
Running
File size: 4,588 Bytes
c6fd460 be5358c c6fd460 be5358c c6fd460 be5358c c6fd460 bddde0e c6fd460 bddde0e defb82f be5358c c6fd460 be5358c defb82f be5358c 031eb10 defb82f 031eb10 defb82f be5358c defb82f be5358c c6fd460 be5358c c6fd460 be5358c c6fd460 bddde0e c6fd460 be5358c c6fd460 be5358c c6fd460 031eb10 c6fd460 be5358c | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 | """
Debug script — inspect mfaytin/mask2former-satellite predictions class by class.
Usage:
python debug_hardscape.py --address "17531 Madison St, Omaha, NE 68135"
python debug_hardscape.py --address "..." --imagery google
This fetches the satellite image for the address and shows what each
semantic class looks like spatially, so we can see what the model
is calling 'building', 'pavement', 'road', etc.
"""
from __future__ import annotations
import argparse
import re
import numpy as np
import torch
import requests
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
from PIL import Image
from transformers import AutoImageProcessor, AutoModelForUniversalSegmentation
from dotenv import load_dotenv
load_dotenv()
from lawn_estimator.config import Config, OUTPUT_DIR # noqa: E402
from lawn_estimator.regions import resolve_region # noqa: E402
from lawn_estimator.sources.google import GoogleStaticMaps # noqa: E402
from lawn_estimator.sources.imagery import CountyOrthoImagery, NaipImagery # noqa: E402
MODEL_ID = "mfaytin/mask2former-satellite"
MODEL_LABELS = {
0: "background",
1: "bareland",
2: "grass",
3: "pavement",
4: "road",
5: "tree",
6: "water",
7: "cropland",
8: "building",
}
def fetch_image(address: str, imagery: str = "naip") -> Image.Image:
config = Config()
session = requests.Session()
region, geocode = resolve_region(address, config, session)
print(f" lat={geocode.latitude:.6f}, lon={geocode.longitude:.6f}")
if imagery == "county":
client = region.display_imagery or CountyOrthoImagery(session=session)
elif imagery == "naip":
client = NaipImagery(session)
else:
client = GoogleStaticMaps(config.google_maps_api_key, session)
return client.fetch_satellite_image(
latitude=geocode.latitude,
longitude=geocode.longitude,
zoom=config.zoom,
image_size=config.image_size,
scale=config.image_scale,
)
def run_model(image: Image.Image) -> np.ndarray:
print(f" Loading {MODEL_ID}...")
processor = AutoImageProcessor.from_pretrained(MODEL_ID)
model = AutoModelForUniversalSegmentation.from_pretrained(MODEL_ID)
model.eval()
inputs = processor(images=image, return_tensors="pt")
with torch.inference_mode():
outputs = model(**inputs)
maps = processor.post_process_semantic_segmentation(
outputs, target_sizes=[image.size[::-1]]
)
return maps[0].detach().cpu().numpy()
def debug(address: str, imagery: str = "naip") -> None:
print(f"\nDebug hardscape model for: {address} (imagery: {imagery})\n")
print("[1/3] Fetching satellite image...")
image = fetch_image(address, imagery)
print(f" Image size: {image.size}")
print("\n[2/3] Running model...")
prediction = run_model(image)
unique = np.unique(prediction)
print("\n Classes detected:")
for code in unique:
label = MODEL_LABELS.get(int(code), f"unknown_{code}")
count = (prediction == code).sum()
print(f" {code}: {label:<15} {count:>8,} px ({count / prediction.size * 100:.1f}%)")
print("\n[3/3] Rendering per-class visualization...")
fig, axes = plt.subplots(3, 3, figsize=(16, 16))
fig.suptitle(f"mask2former-satellite — per-class predictions\n{address}", fontsize=13)
for idx, (code, label) in enumerate(MODEL_LABELS.items()):
ax = axes[idx // 3][idx % 3]
mask = prediction == code
ax.imshow(image, alpha=0.6)
if mask.any():
ax.imshow(
np.ma.masked_where(~mask, np.ones_like(mask, dtype=float)),
cmap="Reds", vmin=0, vmax=1, alpha=0.65,
)
ax.set_title(
f"[{code}] {label}\n{mask.sum():,} px ({mask.sum()/mask.size*100:.1f}%)",
fontsize=10,
)
ax.axis("off")
plt.tight_layout()
out_dir = OUTPUT_DIR
out_dir.mkdir(parents=True, exist_ok=True)
sanitized = re.sub(r"[^\w\s-]", "", address).strip().replace(" ", "_")[:60]
out_path = out_dir / f"debug_hardscape_{sanitized}.png"
plt.savefig(out_path, dpi=120, bbox_inches="tight")
plt.close(fig)
print(f"\n Saved to: {out_path}")
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument(
"--address", type=str,
default="17531 Madison St, Omaha, NE 68135",
)
parser.add_argument("--imagery", choices=["naip", "google", "county"], default="naip")
args = parser.parse_args()
debug(args.address, args.imagery)
|