def test_rebuild_model():
model = Sequential()
model.add(Dense(128, input_shape=(784,)))
model.add(Dense(64))
assert(model.get_layer(index=-1).output_shape == (None, 64))
model.add(Dense(32))
assert(model.get_layer(index=-1).output_shape == (None, 32))
def make_wider_student_model(teacher_model, train_data,
validation_data, init, epochs=3):
'''Train a wider student model based on teacher_model,
with either 'random-pad' (baseline) or 'net2wider'
'''
new_conv1_width = 128
new_fc1_width = 128
model = Sequential()
# a wider conv1 compared to teacher_model
model.add(Conv2D(new_conv1_width, 3, input_shape=input_shape,
padding='same', name='conv1'))
model.add(MaxPooling2D(2, name='pool1'))
model.add(Conv2D(64, 3, padding='same', name='conv2'))
model.add(MaxPooling2D(2, name='pool2'))
model.add(Flatten(name='flatten'))
# a wider fc1 compared to teacher model
model.add(Dense(new_fc1_width, activation='relu', name='fc1'))
model.add(Dense(num_class, activation='softmax', name='fc2'))
# The weights for other layers need to be copied from teacher_model
# to student_model, except for widened layers
# and their immediate downstreams, which will be initialized separately.
# For this example there are no other layers that need to be copied.
w_conv1, b_conv1 = teacher_model.get_layer('conv1').get_weights()
w_conv2, b_conv2 = teacher_model.get_layer('conv2').get_weights()
new_w_conv1, new_b_conv1, new_w_conv2 = wider2net_conv2d(
w_conv1, b_conv1, w_conv2, new_conv1_width, init)
model.get_layer('conv1').set_weights([new_w_conv1, new_b_conv1])
model.get_layer('conv2').set_weights([new_w_conv2, b_conv2])
w_fc1, b_fc1 = teacher_model.get_layer('fc1').get_weights()
w_fc2, b_fc2 = teacher_model.get_layer('fc2').get_weights()
new_w_fc1, new_b_fc1, new_w_fc2 = wider2net_fc(
w_fc1, b_fc1, w_fc2, new_fc1_width, init)
model.get_layer('fc1').set_weights([new_w_fc1, new_b_fc1])
model.get_layer('fc2').set_weights([new_w_fc2, b_fc2])
model.compile(loss='categorical_crossentropy',
optimizer=SGD(lr=0.001, momentum=0.9),
metrics=['accuracy'])
train_x, train_y = train_data
history = model.fit(train_x, train_y,
epochs=epochs,
validation_data=validation_data)
return model, history
def test_get_layer():
model = Sequential()
model.add(Dense(1, input_dim=2))
with pytest.raises(ValueError):
model.get_layer(index=5)
with pytest.raises(ValueError):
model.get_layer(index=None)
with pytest.raises(ValueError):
model.get_layer(name='conv')
def make_deeper_student_model(teacher_model, train_data,
validation_data, init, epochs=3):
'''Train a deeper student model based on teacher_model,
with either 'random-init' (baseline) or 'net2deeper'
'''
model = Sequential()
model.add(Conv2D(64, 3, input_shape=input_shape,
padding='same', name='conv1'))
model.add(MaxPooling2D(2, name='pool1'))
model.add(Conv2D(64, 3, padding='same', name='conv2'))
# add another conv2d layer to make original conv2 deeper
if init == 'net2deeper':
prev_w, _ = model.get_layer('conv2').get_weights()
new_weights = deeper2net_conv2d(prev_w)
model.add(Conv2D(64, 3, padding='same',
name='conv2-deeper', weights=new_weights))
elif init == 'random-init':
model.add(Conv2D(64, 3, padding='same', name='conv2-deeper'))
else:
raise ValueError('Unsupported weight initializer: %s' % init)
model.add(MaxPooling2D(2, name='pool2'))
model.add(Flatten(name='flatten'))
model.add(Dense(64, activation='relu', name='fc1'))
# add another fc layer to make original fc1 deeper
if init == 'net2deeper':
# net2deeper for fc layer with relu, is just an identity initializer
model.add(Dense(64, kernel_initializer='identity',
activation='relu', name='fc1-deeper'))
elif init == 'random-init':
model.add(Dense(64, activation='relu', name='fc1-deeper'))
else:
raise ValueError('Unsupported weight initializer: %s' % init)
model.add(Dense(num_class, activation='softmax', name='fc2'))
# copy weights for other layers
copy_weights(teacher_model, model, layer_names=[
'conv1', 'conv2', 'fc1', 'fc2'])
model.compile(loss='categorical_crossentropy',
optimizer=SGD(lr=0.001, momentum=0.9),
metrics=['accuracy'])
train_x, train_y = train_data
history = model.fit(train_x, train_y,
epochs=epochs,
validation_data=validation_data)
return model, history
