def execute():
(train_data,
train_labels), (test_data,
test_labels) = tf.keras.datasets.reuters.load_data(
num_words=10000)
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
one_hot_train_labels = tf.keras.utils.to_categorical(train_labels)
one_hot_test_labels = tf.keras.utils.to_categorical(test_labels)
x_val = x_train[:1000]
partial_x_train = x_train[1000:]
y_val = one_hot_train_labels[:1000]
partial_y_train = one_hot_train_labels[1000:]
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(64, activation='relu'),
tf.keras.layers.Dense(46, activation='softmax')
])
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))
show_loss(history)
show_accuracy(history)
def execute():
(train_data,
train_labels), (test_data,
test_labels) = tf.keras.datasets.imdb.load_data(
num_words=10000)
y_train = np.asarray(train_labels).astype('float32')
y_test = np.asarray(test_labels).astype('float32')
x_train = vectorize_sequences(train_data)
x_test = vectorize_sequences(test_data)
x_val = x_train[:10000]
partial_x_train = x_train[10000:]
y_val = y_train[:10000]
partial_y_train = y_train[10000:]
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(16, activation='relu'),
tf.keras.layers.Dense(16, activation='relu'),
tf.keras.layers.Dense(1, activation='sigmoid')
])
model.compile(optimizer='rmsprop',
loss='binary_crossentropy',
metrics=['accuracy'])
history = model.fit(partial_x_train,
partial_y_train,
epochs=20,
batch_size=512,
validation_data=(x_val, y_val))
show_loss(history)
show_accuracy(history)
def execute():
train_data = load_npy_file(npy_files_dir_path + 'train_z_data.npy')
valid_data = load_npy_file(npy_files_dir_path + 'valid_z_data.npy')
test_data = load_npy_file(npy_files_dir_path + 'test_z_data.npy')
train_labels = load_npy_file(npy_files_dir_path + 'train_labels.npy')
valid_labels = load_npy_file(npy_files_dir_path + 'valid_labels.npy')
test_labels = load_npy_file(npy_files_dir_path + 'test_labels.npy')
one_hot_train_labels = tf.keras.utils.to_categorical(train_labels)
one_hot_valid_labels = tf.keras.utils.to_categorical(valid_labels)
one_hot_test_labels = tf.keras.utils.to_categorical(test_labels)
model = tf.keras.models.Sequential([
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(512, activation='relu'),
tf.keras.layers.Dense(3, activation='softmax')
])
model.compile(
optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy']
)
history = model.fit(
train_data,
one_hot_train_labels,
epochs=20,
batch_size=512,
validation_data=(valid_data, one_hot_valid_labels)
)
create_dir_if_necessary(model_saving_dir_path)
model.save(model_saving_dir_path + 'model_Z.h5')
loss, acc = model.evaluate(test_data, one_hot_test_labels)
print_loss_acc(loss, acc)
show_loss(history)
show_accuracy(history)