| """The generated kernel must equal the generic interpreter over the same weights, byte for byte, on the dev split.""" | |
| import subprocess | |
| import sys | |
| from pathlib import Path | |
| import score | |
| HERE = Path(__file__).resolve().parent | |
| fs = score.files(sys.argv[1] if len(sys.argv) > 1 else "dev") | |
| bad = tot = 0 | |
| for p in fs: | |
| try: | |
| data = p.read_text("utf-8").replace("\r\n", "\n").encode() | |
| except UnicodeDecodeError: | |
| continue | |
| out = subprocess.run([str(HERE / "pylexnet"), "--classes"], input=data, capture_output=True).stdout | |
| ref = subprocess.run([str(HERE / "pylexnet"), "--interp", "--classes"], input=data, capture_output=True).stdout | |
| tot += len(data) | |
| if out != ref: | |
| bad += 1 | |
| if bad < 4: | |
| i = next((j for j in range(min(len(out), len(ref))) if out[j] != ref[j]), -1) | |
| print("MISMATCH", p, i, out[i] if i >= 0 else len(out), ref[i] if i >= 0 else len(ref), data[max(0, i - 30):i + 10]) | |
| print(f"{len(fs)} files, {tot / 1e6:.1f} MB, files differing from rules: {bad}") | |