Вот сквозной код для захвата градиента с помощью бэкэнда keras. Я вызвал функцию захвата градиента из обратных вызовов model.fit для захвата градиента после окончания каждой эпохи. Этот код совместим как с версиями tenorflow 1.x, так и с tenorflow 2.x, а также я запустил его в colab. Если вы хотите запустить в tenorflow 1.x, замените первый оператор в запрограммируйте %tensorflow_version 1.x
и перезапустите среду выполнения.
Захват градиента модели -
# Importing dependency
%tensorflow_version 2.x
from tensorflow import keras
from tensorflow.keras import backend as K
from tensorflow.keras import datasets
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Activation, Dropout, Flatten, Conv2D, MaxPooling2D
from tensorflow.keras.layers import BatchNormalization
import numpy as np
import tensorflow as tf
tf.keras.backend.clear_session() # For easy reset of notebook state.
tf.compat.v1.disable_eager_execution()
# Import Data
(train_images, train_labels), (test_images, test_labels) = datasets.cifar10.load_data()
# Build Model
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(Flatten())
model.add(Dense(64, activation='relu'))
model.add(Dense(10))
# Model Summary
model.summary()
# Model Compile
model.compile(optimizer='adam',
loss=keras.losses.SparseCategoricalCrossentropy(from_logits=True),
metrics=['accuracy'])
# Define the Gradient Fucntion
epoch_gradient = []
# Define the Gradient Function
def get_gradient_func(model):
grads = K.gradients(model.total_loss, model.trainable_weights)
inputs = model._feed_inputs + model._feed_targets + model._feed_sample_weights
func = K.function(inputs, grads)
return func
# Define the Required Callback Function
class GradientCalcCallback(keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs=None):
get_gradient = get_gradient_func(model)
grads = get_gradient([train_images, train_labels, np.ones(len(train_labels))])
epoch_gradient.append(grads)
epoch = 4
model.fit(train_images, train_labels, epochs=epoch, validation_data=(test_images, test_labels), callbacks=[GradientCalcCallback()])
# (7) Convert to a 2 dimensiaonal array of (epoch, gradients) type
gradient = np.asarray(epoch_gradient)
print("Total number of epochs run:", epoch)
print("Gradient Array has the shape:",gradient.shape)
Вывод -
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) (None, 30, 30, 32) 896
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 15, 15, 32) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 13, 13, 64) 18496
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 6, 6, 64) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 4, 4, 64) 36928
_________________________________________________________________
flatten (Flatten) (None, 1024) 0
_________________________________________________________________
dense (Dense) (None, 64) 65600
_________________________________________________________________
dense_1 (Dense) (None, 10) 650
=================================================================
Total params: 122,570
Trainable params: 122,570
Non-trainable params: 0
_________________________________________________________________
Train on 50000 samples, validate on 10000 samples
Epoch 1/4
50000/50000 [==============================] - 73s 1ms/sample - loss: 1.8199 - accuracy: 0.3834 - val_loss: 1.4791 - val_accuracy: 0.4548
Epoch 2/4
50000/50000 [==============================] - 357s 7ms/sample - loss: 1.3590 - accuracy: 0.5124 - val_loss: 1.2661 - val_accuracy: 0.5520
Epoch 3/4
50000/50000 [==============================] - 377s 8ms/sample - loss: 1.1981 - accuracy: 0.5787 - val_loss: 1.2625 - val_accuracy: 0.5674
Epoch 4/4
50000/50000 [==============================] - 345s 7ms/sample - loss: 1.0838 - accuracy: 0.6183 - val_loss: 1.1302 - val_accuracy: 0.6083
Total number of epochs run: 4
Gradient Array has the shape: (4, 10)
Надеюсь, что это ответ на ваш вопрос. Счастливого обучения.