def run():
file_path = os.path.dirname(
os.path.realpath(__file__)) + "/dlmb_mnist_example.json"
# If a file of the neural-net model's architexture already exists,
# then there is no need to build a new model.
if os.path.isfile(file_path):
# load the model and get its predictions based on x_test
nn_model = Sequential()
nn_model.load(file_path)
predictions = nn_model.predict(x_test)
# compare the predictions to the correct labels
print(
f"This model got a {validate_model(predictions, y_test)/100}% accuracy"
)
# If the file doesn't exist then we need to build a neural-net model and train it.
else:
# Build the neural-net model
nn_model = Sequential([
Dense(
128, 784, activation="ReLU"
), # for the layer_dim we want 128 outputs and 784 inputs (each pixel on the image)
Batchnorm(128),
Dense(128, 128, activation="ReLU"),
Batchnorm(128),
Dense(32, 128, activation="ReLU"),
Batchnorm(32),
Dense(10, 32, activation="Softmax"
) # We have 10 nodes in the layer for each number from 0 - 9
])
nn_model.build(loss="crossentropy", optimizer="adam")
# Crossentropy is a good loss function when you are doing logistic regression (classification)
# Adam is one of the most popular optimizers
nn_model.train(x_train, y_train, epochs=10, batch_size=1000)
# Train the model
# We go through the data 10 times and split the data of 60000 samples into 1000 sized batches leaving 60 samples
# Now we save the model so we can use it again without re-training
nn_model.save(file_path) # When saving, files must end in .json
def main():
# 先讀取資料，並建立模型。
# 輸入的維度為一個資料的長度，因為資料量小，batch size即為資料總數。
x, y = ParityBits(8).load_data()
batch_size, input_dim = x.shape
model = Sequential(
[Dense(64, activation=ReLU()),
Dense(32, activation=Tanh()),
Dense(16, activation=Tanh()),
Dense(4, activation=None),
Dense(1, activation=Sigmoid())],
input_dim=input_dim,
# 使用GD為優化器，MSE為損失函式。
optimizer=GradientDescent(learning_rate=0.01, momentum=0.0),
loss=MeanSquaredError())
# 設定好epochs後訓練模型，訓練完後取得預測結果和每個epoch的損失值。
y_pred, losses = model.train(
x, y, batch_size=batch_size, epochs=200, verbose_step=10)
# 因為答案皆為整數0或1，因此訓練的成果為模型預測的結果取整數。
result = np.around(y_pred).astype(int)
# 將答案與訓練成果相減。
diff = np.subtract(y, result)
print(pd.DataFrame({
# 印出表格時，須將輸入的資料的每項陣列例如`[0 0 0 0 0 0 0 0]`轉成字串，
# 因為Pandas的DataFrame的每一項不能吃陣列。
"Data": [np.array_str(v) for v in x],
"Answer": y[:, 0],
"Prediction": [f'{v:.8f}' for v in y_pred[:, 0]],
"Result": result[:, 0],
# 如果答案與訓練成果在相減之後為0的話代表預測正確，否則失敗。
"Correct": [True if v == 0 else False for v in diff[:, 0]]
}, index=np.arange(1, len(x) + 1)).to_string())
# 輸出最後的損失值和訓練成果與答案差了幾項，並繪製每個epoch與其損失值的變化圖表。
print(f'loss: {losses[-1]:.8f}, difference: {np.count_nonzero(diff)}')
plt.figure(figsize=(8, 4))
plt.plot(losses)
plt.xlabel('epoch')
plt.ylabel('loss')
plt.show()
(train_x, test_x, train_y, test_y) = mnist(data_dir)
(train_x, valid_x, train_y, valid_y) = train_test_split(train_x, train_y, train_size=0.8,
random_state=np.random.randint(10e6))
return (shared(train_x, borrow=True),
shared(test_x, borrow=True),
shared(valid_x, borrow=True),
shared(train_y, borrow=True),
shared(test_y, borrow=True),
shared(valid_y, borrow=True))
(train_x, test_x, valid_x, train_y, test_y, valid_y) = load_data('../data/mnist')
# Shared params
epoch = 5
batch_size = 1000
# Without dropout
model = Sequential(
[FullConnected(784, 625, activation='relu'),
FullConnected(625, 625, activation='relu'),
FullConnected(625, 10, activation='softmax')],
optimizer=RMSprop()
)
model.train(train_x, train_y, epoch=epoch, batch_size=batch_size,
validation_data=(valid_x, valid_y), valid_freq=20, monitor=True)
score = model.score(test_x, test_y)
print('test score: {0}'.format(score.eval()))
if valid > 0:
(train_x, valid_x, train_y, valid_y) = train_test_split(all_x, all_y, train_size=1 - valid)
return (shared(train_x, borrow=True),
shared(test_x, borrow=True),
shared(valid_x, borrow=True),
shared(train_y, borrow=True),
shared(test_y, borrow=True),
shared(valid_y, borrow=True))
else:
return (shared(train_x, borrow=True),
shared(test_x, borrow=True),
shared(train_y, borrow=True),
shared(test_y, borrow=True))
dataset = datasets.load_digits()
(train_x, test_x, valid_x, train_y, test_y, valid_y) = load_data(dataset, valid=0.2)
model = Sequential(
[FullConnected(64, 128),
FullConnected(128, 10, activation='softmax')],
optimizer=SGD(lr=0.0001, decay=.001, momentum=0.9)
)
model.train(train_x, train_y, epoch=100, batch_size=1437,
validation_data=(valid_x, valid_y), valid_freq=5, patience=10,
monitor=True)
score = model.score(test_x, test_y)
print('test score: {0}'.format(score.eval()))
(train_x, valid_x, train_y,
valid_y) = train_test_split(all_x, all_y, train_size=1 - valid)
return (shared(train_x, borrow=True), shared(test_x, borrow=True),
shared(valid_x, borrow=True), shared(train_y, borrow=True),
shared(test_y, borrow=True), shared(valid_y, borrow=True))
else:
return (shared(train_x, borrow=True), shared(test_x, borrow=True),
shared(train_y, borrow=True), shared(test_y, borrow=True))
dataset = datasets.load_digits()
(train_x, test_x, valid_x, train_y, test_y, valid_y) = load_data(dataset,
valid=0.2)
model = Sequential(
[FullConnected(64, 128),
FullConnected(128, 10, activation='softmax')],
optimizer=SGD(lr=0.0001, decay=.001, momentum=0.9))
model.train(train_x,
train_y,
epoch=100,
batch_size=1437,
validation_data=(valid_x, valid_y),
valid_freq=5,
patience=10,
monitor=True)
score = model.score(test_x, test_y)
print('test score: {0}'.format(score.eval()))
return (shared(train_x, borrow=True), shared(test_x, borrow=True),
shared(valid_x, borrow=True), shared(train_y, borrow=True),
shared(test_y, borrow=True), shared(valid_y, borrow=True))
(train_x, test_x, valid_x, train_y, test_y,
valid_y) = load_data('../data/mnist')
# Shared params
epoch = 5
batch_size = 1000
# Without dropout
model = Sequential([
FullConnected(784, 625, activation='relu'),
FullConnected(625, 625, activation='relu'),
FullConnected(625, 10, activation='softmax')
],
optimizer=RMSprop())
model.train(train_x,
train_y,
epoch=epoch,
batch_size=batch_size,
validation_data=(valid_x, valid_y),
valid_freq=20,
monitor=True)
score = model.score(test_x, test_y)
print('test score: {0}'.format(score.eval()))