Create train_model.py

train_model.py

@@ -0,0 +1,81 @@
+# train_model.py
+import numpy as np
+import os
+from glob import glob
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import LSTM, Dense, Dropout, BatchNormalization
+from tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping
+import joblib
+
+DATA_DIR = "gesture_data"
+SEQ_LEN = 30
+MODEL_OUT = "gesture_lstm.h5"
+LABELS_OUT = "labels.joblib"
+
+def load_data(data_dir):
+    X = []
+    y = []
+    for label in sorted(os.listdir(data_dir)):
+        p = os.path.join(data_dir, label)
+        if not os.path.isdir(p): continue
+        files = glob(os.path.join(p, "*.npz"))
+        for f in files:
+            d = np.load(f)['data']
+            if d.shape[0] != SEQ_LEN:
+                continue
+            X.append(d)  # shape (seq_len, features)
+            y.append(label)
+    X = np.array(X)
+    y = np.array(y)
+    return X, y
+
+def build_model(input_shape, num_classes):
+    model = Sequential([
+        LSTM(128, return_sequences=True, input_shape=input_shape),
+        Dropout(0.3),
+        LSTM(64),
+        BatchNormalization(),
+        Dropout(0.3),
+        Dense(64, activation="relu"),
+        Dense(num_classes, activation="softmax")
+    ])
+    model.compile(optimizer="adam", loss="sparse_categorical_crossentropy", metrics=["accuracy"])
+    return model
+
+def main():
+    X, y = load_data(DATA_DIR)
+    print("Loaded X:", X.shape, "y:", y.shape)
+    le = LabelEncoder()
+    y_enc = le.fit_transform(y)
+    joblib.dump(le, LABELS_OUT)
+    X_train, X_test, y_train, y_test = train_test_split(X, y_enc, test_size=0.2, random_state=42, stratify=y_enc)
+    # normalize coords per sample (optional)
+    # Flatten features along coordinates scale? We'll standardize by sample mean/std
+    # Here we scale coords to zero mean unit std per sample for robustness
+    def normalize_samples(arr):
+        arr2 = arr.copy()
+        for i in range(arr2.shape[0]):
+            s = arr2[i]
+            mean = s.mean(axis=0)
+            std = s.std(axis=0) + 1e-8
+            arr2[i] = (s - mean) / std
+        return arr2
+    X_train = normalize_samples(X_train)
+    X_test = normalize_samples(X_test)
+    input_shape = (X_train.shape[1], X_train.shape[2])  # (seq_len, features)
+    model = build_model(input_shape, len(le.classes_))
+    print(model.summary())
+    ckpt = ModelCheckpoint(MODEL_OUT, save_best_only=True, monitor="val_loss", verbose=1)
+    es = EarlyStopping(monitor="val_loss", patience=10, restore_best_weights=True)
+    history = model.fit(X_train, y_train, validation_data=(X_test, y_test),
+                        epochs=100, batch_size=16, callbacks=[ckpt, es])
+    # final evaluation
+    loss, acc = model.evaluate(X_test, y_test)
+    print("Test loss/acc:", loss, acc)
+    print("Saved model to", MODEL_OUT)
+    print("Saved labels to", LABELS_OUT)
+
+if __name__ == "__main__":
+    main()