Initial commit: handshapes multiclass project

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

prep_sequence_resampled.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+# Build fixed-length (N frames) dataset from sequences/<split>/<CLASS>/clip_*.npz
+import argparse, os, glob, json
+from pathlib import Path
+import numpy as np
+
+def resample_sequence(X, N=32):
+    # X: (T,F) -> (N,F) via linear interpolation over frame index
+    T = len(X)
+    if T == 0: return np.zeros((N, X.shape[1]), np.float32)
+    if T == 1: return np.repeat(X, N, axis=0)
+    src = np.linspace(0, T-1, num=T, dtype=np.float32)
+    dst = np.linspace(0, T-1, num=N, dtype=np.float32)
+    out = np.zeros((N, X.shape[1]), np.float32)
+    for d in range(X.shape[1]):
+        out[:, d] = np.interp(dst, src, X[:, d])
+    return out
+
+def load_classes(seq_root: Path):
+    # Accept ANY class subfolder under sequences/train/, ignore hidden/system dirs
+    train_dir = seq_root / "train"
+    if not train_dir.exists():
+        raise SystemExit(f"Missing folder: {train_dir}")
+    classes = sorted([
+        p.name for p in train_dir.iterdir()
+        if p.is_dir() and not p.name.startswith(".")
+    ])
+    if not classes:
+        raise SystemExit("No classes found in sequences/train/ (folders should be class names like Mother, Father, etc.)")
+    return classes
+
+def collect_split(seq_root: Path, split: str, classes, N):
+    Xs, ys = [], []
+    for ci, cls in enumerate(classes):
+        for f in sorted(glob.glob(str(seq_root / split / cls / "clip_*.npz"))):
+            d = np.load(f)
+            Xi = d["X"].astype(np.float32)   # (T,F)
+            XiN = resample_sequence(Xi, N)   # (N,F)
+            Xs.append(XiN); ys.append(ci)
+    if Xs:
+        X = np.stack(Xs, 0); y = np.array(ys, np.int64)
+    else:
+        X = np.zeros((0, N, 1), np.float32); y = np.zeros((0,), np.int64)
+    return X, y
+
+def main():
+    ap = argparse.ArgumentParser()
+    ap.add_argument("--in", dest="in_dir", default="sequences")
+    ap.add_argument("--out", default="landmarks_seq32")
+    ap.add_argument("--frames", type=int, default=32)
+    args = ap.parse_args()
+
+    seq_root = Path(args.in_dir)
+    outdir = Path(args.out); outdir.mkdir(parents=True, exist_ok=True)
+
+    classes = load_classes(seq_root)
+    trX, trY = collect_split(seq_root, "train", classes, args.frames)
+    vaX, vaY = collect_split(seq_root, "val",   classes, args.frames)
+
+    if trX.size == 0 and vaX.size == 0:
+        raise SystemExit("Found no clips. Did you run capture and save any clip_*.npz files?")
+
+    np.save(outdir/"train_X.npy", trX)
+    np.save(outdir/"train_y.npy", trY)
+    np.save(outdir/"val_X.npy",   vaX)
+    np.save(outdir/"val_y.npy",   vaY)
+    json.dump(classes, open(outdir/"class_names.json", "w"))
+
+    # Detect true feature dimension from data
+    input_dim = int(trX.shape[-1] if trX.size else vaX.shape[-1])
+    json.dump({"frames": args.frames, "input_dim": input_dim}, open(outdir/"meta.json","w"))
+
+    print(f"Saved dataset → {outdir}")
+    print(f"  train {trX.shape}, val {vaX.shape}, classes={classes}, input_dim={input_dim}")
+
+if __name__ == "__main__":
+    main()