How to average weights in Keras models, when I train few models with the same architecture with different initialisations?
Now my code looks something like this?
datagen = ImageDataGenerator(rotation_range=15,
width_shift_range=2.0/28,
height_shift_range=2.0/28
)
epochs = 40
lr = (1.234e-3)
optimizer = Adam(lr=lr)
main_input = Input(shape= (28,28,1), name='main_input')
sub_models = []
for i in range(5):
x = Conv2D(32, kernel_size=(3,3), strides=1)(main_input)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPool2D(pool_size=2)(x)
x = Conv2D(64, kernel_size=(3,3), strides=1)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = MaxPool2D(pool_size=2)(x)
x = Conv2D(64, kernel_size=(3,3), strides=1)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Flatten()(x)
x = Dense(1024)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.1)(x)
x = Dense(256)(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.4)(x)
x = Dense(10, activation='softmax')(x)
sub_models.append(x)
x = keras.layers.average(sub_models)
main_output = keras.layers.average(sub_models)
model = Model(inputs=[main_input], outputs=[main_output])
model.compile(loss='categorical_crossentropy', metrics=['accuracy'],
optimizer=optimizer)
print(model.summary())
plot_model(model, to_file='model.png')
filepath="weights.best.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
tensorboard = TensorBoard(log_dir='./Graph', histogram_freq=0, write_graph=True, write_images=True)
callbacks = [checkpoint, tensorboard]
model.fit_generator(datagen.flow(X_train, y_train, batch_size=128),
steps_per_epoch=len(X_train) / 128,
epochs=epochs,
callbacks=callbacks,
verbose=1,
validation_data=(X_test, y_test))
So now I average only last layer, but I want to average weights in all layers after training each one separately.
Thanks!
1 Answer. Show activity on this post. Model weights are all the parameters (including trainable and non-trainable) of the model which are in turn all the parameters used in the layers of the model. And yes, for a convolution layer that would be the filter weights as well as the biases.
Use the get_weights() function to get the weights and biases of the layers before training the model. These are the weights and biases with which the layers will be initialized.
What is Weight (Artificial Neural Network)? Weight is the parameter within a neural network that transforms input data within the network's hidden layers. A neural network is a series of nodes, or neurons. Within each node is a set of inputs, weight, and a bias value.
So let's assume that models
is a collection of your models. First - collect all weights:
weights = [model.get_weights() for model in models]
Now - create a new averaged weights:
new_weights = list()
for weights_list_tuple in zip(*weights):
new_weights.append(
[numpy.array(weights_).mean(axis=0)\
for weights_ in zip(*weights_list_tuple)])
And what is left is to set these weights in a new model:
new_model.set_weights(new_weights)
Of course - averaging weights might be a bad idea, but in case you try - you should follow this approach.
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With