Вот пример, где я извлекал градиенты после каждой эпохи. Вы можете внести изменения в model.fit l oop, чтобы внести свои изменения в слой.
Примечание: Я использовал тензор потока 1.15.0
# (1) Importing dependency
import keras
from keras import backend as K
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout, Flatten, Conv2D, MaxPooling2D
from keras.layers.normalization import BatchNormalization
import numpy as np
np.random.seed(1000)
# (2) Get Data
import tflearn.datasets.oxflower17 as oxflower17
x, y = oxflower17.load_data(one_hot=True)
# (3) Create a sequential model
model = Sequential()
# 1st Convolutional Layer
model.add(Conv2D(filters=96, input_shape=(224,224,3), kernel_size=(11,11), strides=(4,4), padding='valid'))
model.add(Activation('relu'))
# Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))
# Batch Normalisation before passing it to the next layer
model.add(BatchNormalization())
# 2nd Convolutional Layer
model.add(Conv2D(filters=256, kernel_size=(11,11), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
# Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))
# Batch Normalisation
model.add(BatchNormalization())
# 3rd Convolutional Layer
model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
# Batch Normalisation
model.add(BatchNormalization())
# 4th Convolutional Layer
model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
# Batch Normalisation
model.add(BatchNormalization())
# 5th Convolutional Layer
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
# Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))
# Batch Normalisation
model.add(BatchNormalization())
# Passing it to a dense layer
model.add(Flatten())
# 1st Dense Layer
model.add(Dense(4096, input_shape=(224*224*3,)))
model.add(Activation('relu'))
# Add Dropout to prevent overfitting
model.add(Dropout(0.4))
# Batch Normalisation
model.add(BatchNormalization())
# 2nd Dense Layer
model.add(Dense(4096))
model.add(Activation('relu'))
# Add Dropout
model.add(Dropout(0.4))
# Batch Normalisation
model.add(BatchNormalization())
# 3rd Dense Layer
model.add(Dense(1000))
model.add(Activation('relu'))
# Add Dropout
model.add(Dropout(0.4))
# Batch Normalisation
model.add(BatchNormalization())
# Output Layer
model.add(Dense(17))
model.add(Activation('softmax'))
model.summary()
# (4) Compile
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# (5) Define Gradient Function
def get_gradient_func(model):
grads = K.gradients(model.total_loss, model.trainable_weights)
inputs = model.model._feed_inputs + model.model._feed_targets + model.model._feed_sample_weights
func = K.function(inputs, grads)
return func
# (6) Train the model such that gradients are captured for every epoch
epoch_gradient = []
for epoch in range(1,5):
model.fit(x, y, batch_size=64, epochs= epoch, initial_epoch = (epoch-1), verbose=1, validation_split=0.2, shuffle=True)
get_gradient = get_gradient_func(model)
grads = get_gradient([x, y, np.ones(len(y))])
# Similarly define your function to play with your model.layers,model.layers[].get_weights(),model.input,model.total_loss,model.trainable_weights etc
# print("Layer of the model:",model.layers[2])
# print("Weights of the Layer",model.layers[2].get_weights())
# print(model.input)
# print(model.total_loss)
# print(model.trainable_weights)
epoch_gradient.append(grads)
# (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)