scripts/02_resize_images.py

import cv2
import pandas as pd
from pathlib import Path

IN_IMG = Path("data_merged/images")
OUT_IMG = Path("data_processed/images")
IN_CSV = Path("data_merged/metadata_raw.csv")
OUT_CSV = Path("data_processed/metadata_resized.csv")

OUT_IMG.mkdir(parents=True, exist_ok=True)

df = pd.read_csv(IN_CSV)
kept_rows = []

for _, row in df.iterrows():
    src = IN_IMG / row["filename"]
    dst = OUT_IMG / row["filename"]

    img = cv2.imread(str(src))
    if img is None:
        continue

    img = cv2.resize(img, (224, 224))
    cv2.imwrite(str(dst), img)

    kept_rows.append(row)

pd.DataFrame(kept_rows).to_csv(OUT_CSV, index=False)

print("Images kept:", len(kept_rows))