def top_level_task():
num_classes = 10
img_rows, img_cols = 28, 28
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
print("shape: ", x_train.shape, x_train.__array_interface__["strides"])
# model = Sequential()
# model.add(Conv2D(filters=32, input_shape=(1,28,28), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
# model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
# model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
# model.add(Flatten())
# model.add(Dense(128, activation="relu"))
# model.add(Dense(num_classes))
# model.add(Activation("softmax"))
layers = [
Conv2D(filters=32,
input_shape=(1, 28, 28),
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"),
Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"),
Flatten(),
Dense(128, activation="relu"),
Dense(num_classes),
Activation("softmax")
]
model = Sequential(layers)
print(model.summary())
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
model.fit(x_train, y_train, epochs=1)
def top_level_task():
num_classes = 10
img_rows, img_cols = 28, 28
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
print("shape: ", x_train.shape, x_train.__array_interface__["strides"])
layers = [
Input(shape=(1, 28, 28), dtype="float32"),
Conv2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"),
Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"),
MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"),
Flatten(),
Dense(128, activation="relu"),
Dense(num_classes),
Activation("softmax")
]
model = Sequential(layers)
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit(x_train,
y_train,
epochs=5,
callbacks=[
VerifyMetrics(ModelAccuracy.MNIST_CNN),
EpochVerifyMetrics(ModelAccuracy.MNIST_CNN)
])
def create_student_model_cnn(teacher_model, num_classes, x_train, y_train):
conv1 = teacher_model.get_layer(index=0)
c1_kernel, c1_bias = conv1.get_weights(teacher_model.ffmodel)
print(c1_kernel.shape, c1_bias.shape)
conv2 = teacher_model.get_layer(index=1)
c2_kernel, c2_bias = conv2.get_weights(teacher_model.ffmodel)
dense1 = teacher_model.get_layer(index=4)
d1_kernel, d1_bias = dense1.get_weights(teacher_model.ffmodel)
dense2 = teacher_model.get_layer(index=5)
d2_kernel, d2_bias = dense2.get_weights(teacher_model.ffmodel)
model = Sequential()
model.add(Conv2D(filters=32, input_shape=(1,28,28), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
model.add(Flatten())
model.add(Dense(128, activation="relu", name="dense1"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy', 'sparse_categorical_crossentropy'])
conv1s = model.get_layer(index=0)
conv2s = model.get_layer(index=1)
dense1s = model.get_layer(name="dense1")
dense2s = model.get_layer(index=5)
conv1s.set_weights(model.ffmodel, c1_kernel, c1_bias)
conv2s.set_weights(model.ffmodel, c2_kernel, c2_bias)
dense1s.set_weights(model.ffmodel, d1_kernel, d1_bias)
dense2s.set_weights(model.ffmodel, d2_kernel, d2_bias)
print(model.summary())
model.fit(x_train, y_train, epochs=5, callbacks=[VerifyMetrics(ModelAccuracy.MNIST_CNN), EpochVerifyMetrics(ModelAccuracy.MNIST_CNN)])
def create_teacher_model_cnn(num_classes, x_train, y_train):
model = Sequential()
model.add(Conv2D(filters=32, input_shape=(1,28,28), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
model.add(Flatten())
model.add(Dense(128, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit(x_train, y_train, epochs=5)
return model
def top_level_task():
num_classes = 10
num_samples = 10000
(x_train, y_train), (x_test, y_test) = cifar10.load_data(num_samples)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
print("shape: ", x_train.shape)
model = Sequential()
model.add(
Conv2D(filters=32,
input_shape=(3, 32, 32),
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"))
model.add(
Conv2D(filters=32,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"))
model.add(
Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"))
model.add(
Conv2D(filters=64,
kernel_size=(3, 3),
strides=(1, 1),
padding=(1, 1),
activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2), strides=(2, 2), padding="valid"))
model.add(Flatten())
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.02)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit(x_train,
y_train,
epochs=30,
callbacks=[
VerifyMetrics(ModelAccuracy.CIFAR10_CNN),
EpochVerifyMetrics(ModelAccuracy.CIFAR10_CNN)
])
def top_level_task():
num_classes = 10
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
#y_train = np.random.randint(1, 9, size=(len(y_train),1), dtype='int32')
print("shape: ", x_train.shape)
model = Sequential()
model.add(Dense(512, input_shape=(784, ), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
print(model.summary())
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
model.fit(x_train, y_train, epochs=1)
def top_level_task():
num_classes = 10
num_samples = 10000
(x_train, y_train), (x_test, y_test) = cifar10.load_data(num_samples)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
print("shape: ", x_train.shape)
model1 = Sequential()
model1.add(Conv2D(filters=32, input_shape=(3,32,32), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu", name="conv2d_0_0"))
model1.add(Conv2D(filters=32, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu", name="conv2d_1_0"))
print(model1.summary())
model2 = Sequential()
model2.add(Conv2D(filters=32, input_shape=(3,32,32), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu", name="conv2d_0_1"))
model2.add(Conv2D(filters=32, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu", name="conv2d_1_1"))
print(model2.summary())
output_tensor = Concatenate(axis=1)([model1.output, model2.output])
output_tensor = MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid")(output_tensor)
output_tensor = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu", name="conv2d_0_4")(output_tensor)
output_tensor = Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu")(output_tensor)
output_tensor = MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid")(output_tensor)
output_tensor = Flatten()(output_tensor)
output_tensor = Dense(512, activation="relu")(output_tensor)
output_tensor = Dense(num_classes)(output_tensor)
output_tensor = Activation("softmax")(output_tensor)
model = Model([model1.input[0], model2.input[0]], output_tensor)
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit([x_train, x_train], y_train, epochs=40, callbacks=[VerifyMetrics(ModelAccuracy.CIFAR10_CNN), EpochVerifyMetrics(ModelAccuracy.CIFAR10_CNN)])
def top_level_task():
num_classes = 10
num_samples = 10000
(x_train, y_train), (x_test, y_test) = cifar10.load_data(num_samples)
x_train = x_train.astype('float32')
x_train /= 255
#x_train *= 0
#y_train = np.random.randint(1, 9, size=(num_samples,1), dtype='int32')
y_train = y_train.astype('int32')
print("shape: ", x_train.shape)
model = Sequential()
model.add(Conv2D(filters=32, input_shape=(3,32,32), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(Conv2D(filters=32, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
model.add(Flatten())
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
print(model.summary())
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
model.fit(x_train, y_train, epochs=1)
def top_level_task():
max_words = 1000
epochs = 5
print('Loading data...')
(x_train, y_train), (x_test,
y_test) = reuters.load_data(num_words=max_words,
test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
x_train = x_train.astype('float32')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
print('y_train shape:', y_train.shape)
model = Sequential()
model.add(Input(shape=(max_words, )))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit(x_train,
y_train,
epochs=epochs,
callbacks=[VerifyMetrics(ModelAccuracy.REUTERS_MLP)])
def top_level_task():
num_classes = 10
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_train = x_train.astype('float32')
x_train /= 255
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
print("shape: ", x_train.shape)
model = Sequential()
d1 = Dense(512, input_shape=(784,), kernel_initializer=GlorotUniform(123), bias_initializer=Zeros())
model.add(d1)
model.add(Activation('relu'))
model.add(Dropout(0.2))
model.add(Dense(512, activation="relu"))
model.add(Dropout(0.2))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt, loss='sparse_categorical_crossentropy', metrics=['accuracy', 'sparse_categorical_crossentropy'])
print(model.summary())
model.fit(x_train, y_train, epochs=20, callbacks=[VerifyMetrics(ModelAccuracy.MNIST_MLP), EpochVerifyMetrics(ModelAccuracy.MNIST_MLP)])
model.evaluate(x=x_train, y=y_train)
def create_student_model_cnn(teacher_model, num_classes, x_train, y_train):
conv1 = teacher_model.get_layer(0)
c1_kernel, c1_bias = conv1.get_weights(teacher_model.ffmodel)
print(c1_kernel.shape, c1_bias.shape)
conv2 = teacher_model.get_layer(1)
c2_kernel, c2_bias = conv2.get_weights(teacher_model.ffmodel)
dense1 = teacher_model.get_layer(4)
d1_kernel, d1_bias = dense1.get_weights(teacher_model.ffmodel)
dense2 = teacher_model.get_layer(5)
d2_kernel, d2_bias = dense2.get_weights(teacher_model.ffmodel)
model = Sequential()
model.add(Conv2D(filters=32, input_shape=(1,28,28), kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(Conv2D(filters=64, kernel_size=(3,3), strides=(1,1), padding=(1,1), activation="relu"))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding="valid"))
model.add(Flatten())
model.add(Dense(128, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
conv1s = model.get_layer(0)
conv2s = model.get_layer(1)
dense1s = model.get_layer(4)
dense2s = model.get_layer(5)
conv1s.set_weights(model.ffmodel, c1_kernel, c1_bias)
conv2s.set_weights(model.ffmodel, c2_kernel, c2_bias)
dense1s.set_weights(model.ffmodel, d1_kernel, d1_bias)
dense2s.set_weights(model.ffmodel, d2_kernel, d2_bias)
print(model.summary())
model.fit(x_train, y_train, epochs=1)
def create_teacher_model(num_classes, x_train, y_train):
model = Sequential()
model.add(Dense(512, input_shape=(784,), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
model.fit(x_train, y_train, epochs=1)
dense3 = model.get_layer(2)
d3_kernel, d3_bias = dense3.get_weights(model.ffmodel)
print(d3_bias)
d3_kernel = np.reshape(d3_kernel, (d3_kernel.shape[1], d3_kernel.shape[0]))
print(d3_kernel)
return model
def create_student_model(teacher_model, num_classes, x_train, y_train):
dense1 = teacher_model.get_layer(0)
d1_kernel, d1_bias = dense1.get_weights(teacher_model.ffmodel)
print(d1_kernel.shape, d1_bias.shape)
# print(d1_kernel)
# print(d1_bias)
dense2 = teacher_model.get_layer(1)
d2_kernel, d2_bias = dense2.get_weights(teacher_model.ffmodel)
dense3 = teacher_model.get_layer(2)
d3_kernel, d3_bias = dense3.get_weights(teacher_model.ffmodel)
model = Sequential()
model.add(Dense(512, input_shape=(784,), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt)
dense1s = model.get_layer(0)
dense2s = model.get_layer(1)
dense3s = model.get_layer(2)
dense1s.set_weights(model.ffmodel, d1_kernel, d1_bias)
dense2s.set_weights(model.ffmodel, d2_kernel, d2_bias)
dense3s.set_weights(model.ffmodel, d3_kernel, d3_bias)
d3_kernel, d3_bias = dense3s.get_weights(model.ffmodel)
print(d3_kernel)
print(d3_bias)
model.fit(x_train, y_train, epochs=1)
def create_student_model_mlp(teacher_model, num_classes, x_train, y_train):
dense1 = teacher_model.get_layer(index=0)
d1_kernel, d1_bias = dense1.get_weights(teacher_model.ffmodel)
print(d1_kernel.shape, d1_bias.shape)
dense2 = teacher_model.get_layer(index=1)
d2_kernel, d2_bias = dense2.get_weights(teacher_model.ffmodel)
dense3 = teacher_model.get_layer(index=2)
d3_kernel, d3_bias = dense3.get_weights(teacher_model.ffmodel)
model = Sequential()
model.add(Dense(512, input_shape=(784, ), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy', 'sparse_categorical_crossentropy'])
dense1s = model.get_layer(index=0)
dense2s = model.get_layer(index=1)
dense3s = model.get_layer(index=2)
dense1s.set_weights(model.ffmodel, d1_kernel, d1_bias)
dense2s.set_weights(model.ffmodel, d2_kernel, d2_bias)
dense3s.set_weights(model.ffmodel, d3_kernel, d3_bias)
d3_kernel, d3_bias = dense3s.get_weights(model.ffmodel)
print(d3_kernel)
print(d3_bias)
model.fit(x_train,
y_train,
epochs=5,
callbacks=[
VerifyMetrics(ModelAccuracy.MNIST_MLP),
EpochVerifyMetrics(ModelAccuracy.MNIST_MLP)
])
def create_teacher_model_mlp(num_classes, x_train, y_train):
model = Sequential()
model.add(Dense(512, input_shape=(784, ), activation="relu"))
model.add(Dense(512, activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.SGD(learning_rate=0.01)
model.compile(optimizer=opt,
loss='sparse_categorical_crossentropy',
metrics=['accuracy', 'sparse_categorical_crossentropy'])
model.fit(x_train, y_train, epochs=1)
dense3 = model.get_layer(index=2)
d3_kernel, d3_bias = dense3.get_weights(model.ffmodel)
print(d3_bias)
d3_kernel = np.reshape(d3_kernel, (d3_kernel.shape[1], d3_kernel.shape[0]))
print(d3_kernel)
return model
def top_level_task():
max_words = 1000
epochs = 5
print('Loading data...')
(x_train, y_train), (x_test,
y_test) = reuters.load_data(num_words=max_words,
test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')
num_classes = np.max(y_train) + 1
print(num_classes, 'classes')
print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
x_train = x_train.astype('float32')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)
y_train = y_train.astype('int32')
y_train = np.reshape(y_train, (len(y_train), 1))
print('y_train shape:', y_train.shape)
model = Sequential()
model.add(Dense(512, input_shape=(max_words, ), activation="relu"))
model.add(Dense(num_classes))
model.add(Activation("softmax"))
opt = flexflow.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=opt)
model.fit(x_train, y_train, epochs=epochs)
