File size: 2,746 Bytes
53becf5 | 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 | """Evaluate reconstruction and cross-sensor representation consistency."""
import json
from pathlib import Path
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
import yaml
ROOT = Path(__file__).resolve().parents[1]
def main():
config = yaml.safe_load((ROOT / "conf/config.yaml").read_text())
predictions = np.load(ROOT / config["paths"]["inference_dir"] / "predictions.npz")
sensors = list(config["data"]["sensors"])
metrics = {"samples": int(len(predictions["class_target"])), "sensors": {}}
projected = []
for name in sensors:
embedding = predictions[f"embedding_{name}"]
projection = predictions[f"projected_embedding_{name}"]
projected.append(projection)
metrics["sensors"][name] = {
"reconstruction_mae": float(np.abs(predictions[f"reconstruction_{name}"] - predictions[f"pixels_{name}"]).mean()),
"embedding_norm": float(np.linalg.norm(embedding, axis=1).mean()),
"projected_embedding_norm": float(np.linalg.norm(projection, axis=1).mean()),
"representation_loss": float(predictions[f"representation_loss_{name}"]),
}
similarities = []
for left in range(len(projected)):
for right in range(left + 1, len(projected)):
similarities.append((projected[left] * projected[right]).sum(axis=1))
metrics["mean_cross_sensor_cosine_similarity"] = float(np.concatenate(similarities).mean())
output_dir = ROOT / config["paths"]["evaluation_dir"]
output_dir.mkdir(parents=True, exist_ok=True)
(output_dir / "metrics.json").write_text(json.dumps(metrics, indent=2) + "\n")
figure, axes = plt.subplots(len(sensors), 3, figsize=(9, 3 * len(sensors)), squeeze=False)
for row, name in enumerate(sensors):
rgb = config["data"]["sensors"][name]["rgb_indices"]
source = predictions[f"pixels_{name}"][0, rgb].transpose(1, 2, 0)
reconstruction = predictions[f"reconstruction_{name}"][0, rgb].transpose(1, 2, 0)
for image in (source, reconstruction):
image -= image.min()
image /= image.max() + 1e-6
axes[row, 0].imshow(source)
axes[row, 0].set_title(f"{name} input")
axes[row, 1].imshow(reconstruction)
axes[row, 1].set_title("MAE reconstruction")
axes[row, 2].imshow(np.abs(source - reconstruction).mean(axis=2), cmap="magma")
axes[row, 2].set_title("absolute error")
for axis in axes[row]:
axis.axis("off")
figure.tight_layout()
figure.savefig(output_dir / "comparison.png", dpi=150)
plt.close(figure)
print(f"metrics={output_dir.relative_to(ROOT) / 'metrics.json'}")
if __name__ == "__main__":
main()
|