ocr-projects-archive / OCR_INDRA /tools /exp /padding_variants.py
prosperious's picture
Add 1000 files (OCR_INDRA/.gitignore ...)
f9bc0c1 verified
Raw History Blame Contribute Delete
3.32 kB
import json
from pathlib import Path
import cv2
import numpy as np
import onnxruntime as ort
from indra.indra_ocr.vocab import Vocab
from indra.indra_ocr.rec_preproc import pad_batch
from tools.exp.common import collapseIds, lev, norm
home = Path.home()
data = home / "ocr/ocr-deva-ft/data/chunks-v4/test"
manifest = Path("results/stratified_1500/sample_manifest.jsonl")
model = Path("models/indra-ocr-v3.1.1/rec.onnx")
outdir = Path("results/padding_variants")
outdir.mkdir(parents=True, exist_ok=True)
if not manifest.is_file():
raise FileNotFoundError(f"Missing baseline manifest: {manifest}")
rows = [json.loads(line) for line in manifest.read_text(encoding="utf-8").splitlines() if line.strip()]
if len(rows) != 1500:
raise RuntimeError(f"Expected 1500 manifest rows, got {len(rows)}")
session = ort.InferenceSession(str(model), providers=["CPUExecutionProvider"])
vocab = Vocab.multi()
variants = {
"baseline": (0.00, 0.00),
"small_pad": (0.05, 0.10),
"moderate_pad": (0.20, 0.30),
}
results = []
for i, row in enumerate(rows, 1):
path = data / row["image"]
gray = cv2.imread(str(path), cv2.IMREAD_GRAYSCALE)
if gray is None:
raise RuntimeError(f"Cannot read {path}")
h, w = gray.shape
for name, (pad_y, pad_x) in variants.items():
py, px = round(h * pad_y), round(h * pad_x)
padded = cv2.copyMakeBorder(
gray, py, py, px, px, cv2.BORDER_CONSTANT,
value=255
)
ph, pw = padded.shape
target_w = max(8, min(4096, round(pw * 32 / ph)))
interp = cv2.INTER_AREA if ph > 32 else cv2.INTER_LINEAR
resized = cv2.resize(padded, (target_w, 32), interpolation=interp)
ink = 1.0 - resized.astype(np.float32) / 255.0
x, widths = pad_batch([ink])
ids, conf, lengths = session.run(
["ids", "conf", "lengths"],
{"x": x, "widths": widths.astype(np.int64)}
)
seq = ids[0, :int(lengths[0])].tolist()
pred = vocab.decode(collapseIds(seq))
ref, hyp = norm(row["text"]), norm(pred)
results.append({
"image": row["image"],
"edition": row["edition"],
"variant": name,
"ground_truth": row["text"],
"prediction": pred,
"edits": lev(ref, hyp),
"reference_chars": len(ref),
"exact_match": int(ref == hyp),
})
if i % 100 == 0:
print(f"Processed {i}/{len(rows)} images")
output = outdir / "predictions.jsonl"
with output.open("w", encoding="utf-8") as f:
for r in results:
f.write(json.dumps(r, ensure_ascii=False) + "\n")
print("\n=== PADDING VARIANT RESULTS ===")
for edition in ["2082-03-24", "2082-08-12", "2082-12-25", "ALL"]:
print(f"\nEdition: {edition}")
for name in variants:
subset = [r for r in results if r["variant"] == name and (edition == "ALL" or r["edition"] == edition)]
edits = sum(r["edits"] for r in subset)
chars = sum(r["reference_chars"] for r in subset)
exact = sum(r["exact_match"] for r in subset)
print(f" {name}: exact={exact}/{len(subset)} ({100*exact/max(len(subset),1):.2f}%), CER={100*edits/max(chars,1):.4f}% ({edits}/{chars})")
print("\nPredictions:", output)
print("Providers:", session.get_providers())