How to load imagenet weights before Training in Keras for AlexNet?

Question

Hi I wrote AlexNet in keras using the sequential method. I wanted to know if and how I can load imagenet weights for training the model?

At the moment I am using randomNormal kernel initialization for each layer. But I want to use the imagenet weights for training. I have the weights as a H5 file. Could someone please give an example code as well?

Answer 1

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’))
# Max Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding=’valid’))

# 2nd Convolutional Layer
model.add(Conv2D(filters=256, kernel_size=(11,11), strides=(1,1), padding=’valid’))
model.add(Activation(‘relu’))
# Max Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding=’valid’))

# 3rd Convolutional Layer
model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding=’valid’))
model.add(Activation(‘relu’))

# 4th Convolutional Layer
model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding=’valid’))
model.add(Activation(‘relu’))

# 5th Convolutional Layer
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), padding=’valid’))
model.add(Activation(‘relu’))
# Max Pooling
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding=’valid’))

# Passing it to a Fully Connected layer
model.add(Flatten())
# 1st Fully Connected Layer
model.add(Dense(4096, input_shape=(224*224*3,)))
model.add(Activation(‘relu’))
# Add Dropout to prevent overfitting
model.add(Dropout(0.4))

# 2nd Fully Connected Layer
model.add(Dense(4096))
model.add(Activation(‘relu’))
# Add Dropout
model.add(Dropout(0.4))

# 3rd Fully Connected Layer
model.add(Dense(1000))
model.add(Activation(‘relu’))
# Add Dropout
model.add(Dropout(0.4))

# Output Layer
model.add(Dense(17))
model.add(Activation(‘softmax’))

model.summary()

# Compile the model
model.compile(loss=keras.losses.categorical_crossentropy, optimizer=’adam’, metrics=[“accuracy”])

model.load_weights('weight.h5')