def train(model_dir, cnn_model, saved_model=None,
learning_rate = 1e-5, decay=1e-6,
train_size = 0.8, seq_length=16,
hidden_units=256, dense_units=256, reg=1e-1, dropout_rate=1e-1,
num_classes=6, batch_size=16, nb_epoch=100,
image_shape=None):
# ---- CALL BACK FUNCTIONS FOR FIT_GENERATOR() ---- #
checkpoints_dir = os.path.join(model_dir, 'checkpoints')
if not os.path.exists(checkpoints_dir):
os.makedirs(checkpoints_dir)
checkpointer = ModelCheckpoint(
filepath=os.path.join(checkpoints_dir, 'lstm_weights.{epoch:004d}-{val_loss:.3f}.hdf5'),
verbose=1, save_best_only=False, period=50)
# tensorboard info
tb = TensorBoard(log_dir=model_dir)
# ------------------------------------------------- #
# PREPARE DATASET
dataset = DataSet(cnn_model, seq_length)
# steps_per_epoch = number of batches in one epoch
steps_per_epoch = (len(dataset.data) * train_size) // batch_size
# create train and validation generators
generator = dataset.frame_generator(batch_size, 'train')
# val_generator = dataset.frame_generator(batch_size, 'validation') # use all validation data each time?
(X_val, y_val) = dataset.generate_data('validation')
# load or create model
if saved_model:
rnn_model = load_model(saved_model)
else:
rnn_model = lstm(hidden_units=hidden_units, dense_units=dense_units,
reg=reg, dropout_rate=dropout_rate,
seq_length=seq_length, num_classes=num_classes)
# setup optimizer: ADAM algorithm
optimizer = Adam(lr=learning_rate, decay=decay)
# metrics for judging performance of model
metrics = ['categorical_accuracy'] # ['accuracy'] # if using 'top_k_categorical_accuracy', must specify k
rnn_model.compile(loss='categorical_crossentropy', optimizer=optimizer,
metrics=metrics)
print(rnn_model.summary())
# use fit generator to generate data on the fly
history = rnn_model.fit_generator(generator=generator,
steps_per_epoch=steps_per_epoch,
epochs=nb_epoch,
verbose=1,
callbacks=[tb, checkpointer],
validation_data=(X_val, y_val),
validation_steps=1) # using all validation data for better metrics
return history
rnn_model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=metrics)
# load saved weights
# folder_path = 'experiments/base_model/base_model_dropout_rate_0.00e+00/checkpoints/'
folder_path = 'experiments/base_model/base_model_dropout_rate_3.00e-01/checkpoints/'
saved_weights = os.path.join(folder_path, 'lstm_weights.0300-0.619.hdf5')
rnn_model.load_weights(saved_weights)
# load and prepare test set
dataset = DataSet(cnn_model)
X_train, Y_train = dataset.generate_data('train')
X_val, Y_val = dataset.generate_data('validation')
X_test, Y_test = dataset.generate_data('test')
score = rnn_model.evaluate(x=X_train, y=Y_train, verbose=1)
print("Train Loss: %2.3f" % score[0])
print("Train Accuracy: %1.3f\n" % score[1])
score = rnn_model.evaluate(x=X_val, y=Y_val, verbose=1)
print("Val Loss: %2.3f" % score[0])
print("Val Accuracy: %1.3f\n" % score[1])
score = rnn_model.evaluate(x=X_test, y=Y_test, verbose=1)
print("Test Loss: %2.3f" % score[0])
print("Test Accuracy: %1.3f\n" % score[1])