train_hand_KERAS.py

import csv
import numpy as np
import tensorflow as tf
from sklearn.model_selection import train_test_split

dataset = 'data/hand/data.csv'
model_save_path = 'hand.hdf5'

NUM_CLASSES = 13

X_dataset = np.loadtxt(dataset, delimiter=',', dtype='float32', usecols=list(range(1, (21 * 2) + 1)))
y_dataset = np.loadtxt(dataset, delimiter=',', dtype='int32', usecols=(0))
X_train, X_test, y_train, y_test = train_test_split(X_dataset, y_dataset, train_size=0.75, random_state=42)

model = tf.keras.models.Sequential([
    tf.keras.layers.Input((21 * 2,)),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(30, activation='relu'),
    tf.keras.layers.BatchNormalization(),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Dense(15, activation='relu'),
    tf.keras.layers.Dense(NUM_CLASSES, activation='softmax')
])

model.summary()

cp_callback = tf.keras.callbacks.ModelCheckpoint(model_save_path, verbose=1, save_weights_only=False)

es_callback = tf.keras.callbacks.EarlyStopping(patience=20, verbose=1)

# Model compilation
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(X_train,
          y_train,
          epochs=1000,
          batch_size=128,
          validation_data=(X_test, y_test),
          callbacks=[cp_callback, es_callback])

model = tf.keras.models.load_model(model_save_path)

# Save as a model dedicated to inference
model.save(model_save_path, include_optimizer=False)