def train(model_type, epochs, batch_size, logdir):
ds_train, ds_test = tfds.load('cifar10',
split=['train', 'test'],
as_supervised=True)
num_samples = 50000
num_samples_test = 10000
ds_train = ds_train.shuffle(num_samples)\
.batch(batch_size)\
.map(preprocess, num_parallel_calls=tf.data.experimental.AUTOTUNE)\
.repeat(epochs)\
.prefetch(buffer_size=tf.data.experimental.AUTOTUNE)
ds_test = ds_test.batch(batch_size)\
.map(preprocess, num_parallel_calls=tf.data.experimental.AUTOTUNE)\
.repeat(epochs)\
.prefetch(buffer_size=tf.data.experimental.AUTOTUNE)
kl_div_fn = (lambda q, p, _: tfd.kl_divergence(q, p) / num_samples)
if model_type == 'normal':
model = CNN(num_classes=10)
elif model_type == 'reparam':
model = ReparamCNN(num_classes=10, kernel_divergence_fn=kl_div_fn)
else:
model = FlipOutCNN(num_classes=10, kernel_divergence_fn=kl_div_fn)
# Set input_shape explicitly (before compile) to instantiate model.losses
model.build(input_shape=[None, 32, 32, 3])
optimizer = optimizers.Adam()
loss_fn = losses.SparseCategoricalCrossentropy(from_logits=True)
metrics = [tf.keras.metrics.SparseCategoricalAccuracy(name='accuracy')]
model.compile(optimizer, loss=loss_fn, metrics=metrics)
callbacks = [tf.keras.callbacks.TensorBoard(log_dir=logdir)]
model.fit(ds_train,
epochs=epochs,
callbacks=callbacks,
validation_data=ds_test,
steps_per_epoch=num_samples // batch_size,
validation_steps=num_samples_test // batch_size)
return None
#convert the list to array
X = np.array(X)
X = X / 255.0
y = np.array(y)
y = y.reshape(-1, 1)
y = to_categorical(y)
#split train and test set
trainX, testX, trainY, testY = train_test_split(X,
y,
test_size=0.2,
random_state=1)
print(trainX.shape, trainY.shape)
print(testX.shape, testY.shape)
cnn = CNN(size, numOfLabels)
#build CNN model
model = cnn.build()
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(trainX, trainY, epochs=10, batch_size=BATCH)
_, acc = model.evaluate(testX, testY)
print("accuracy: %.2f%%" % (acc * 100))
model.save(args['save'] + '.h5')
