python之Tensorflow:更新不可训练模型层的权重

我有一个训练有素的模型，它是使用 Keras 创建的。在这个模型上，我想通过卡住除最后一个卷积层以外的所有层来应用迁移学习。但是，当我在卡住层后拟合模型时，我注意到一些卡住层具有不同的权重。我怎样才能避免这种情况？

我尝试使用 model.trainable = False 卡住整个模型，但这也没有成功。

我正在使用 python 3.5.0、tensorflow 1.0.1 和 Keras 2.0.3

示例脚本

import os 
import timeit 
import datetime 
import numpy as np 
from keras.layers.core import Activation, Reshape, Permute 
from keras.layers.convolutional import Convolution2D, MaxPooling2D, UpSampling2D, ZeroPadding2D 
from keras.layers.normalization import BatchNormalization 
from keras.optimizers import Adam 
from keras import models 
from keras import backend as K 
K.set_image_dim_ordering('th') 
 
def conv_model(input_shape, data_shape, kern_size, filt_size, pad_size,\ 
                               maxpool_size, n_classes, compile_model=True): 
    """ 
    Create a small conv neural network 
    input_shape: input shape of the images 
    data_shape: 1d shape of the data 
    kern_size: Kernel size used in all convolutional2d layers 
    filt_size: Filter size of the first and last convolutional2d layer 
    pad_size: size of padding 
    maxpool_size: Pool size of all maxpooling2d and upsampling2d layers 
    n_classes: number of output classes 
    compile_model: True if the model should be compiled 
 
    output: Keras deep learning model 
    """ 
    #keep track of compilation time 
    start_time = timeit.default_timer() 
    model = models.Sequential() 
    # Add a noise layer to get a denoising autoencoder. This helps avoid overfitting 
    model.add(ZeroPadding2D(padding=(pad_size, pad_size), input_shape=input_shape)) 
 
    #Encoding layers 
    model.add(Convolution2D(filt_size, kern_size, kern_size, border_mode='valid')) 
    model.add(BatchNormalization()) 
    model.add(Activation('relu')) 
    model.add(MaxPooling2D(pool_size=(maxpool_size, maxpool_size))) 
    model.add(UpSampling2D(size=(maxpool_size, maxpool_size))) 
    model.add(ZeroPadding2D(padding=(pad_size, pad_size))) 
    model.add(Convolution2D(filt_size, kern_size, kern_size, border_mode='valid')) 
    model.add(BatchNormalization()) 
    model.add(Convolution2D(n_classes, 1, 1, border_mode='valid')) 
    model.add(Reshape((n_classes, data_shape), input_shape=(n_classes,)+input_shape[1:])) 
    model.add(Permute((2, 1))) 
    model.add(Activation('softmax')) 
 
    if compile_model: 
        model.compile(loss="categorical_crossentropy", optimizer='adam', metrics=["accuracy"]) 
    print('Model compiled in {0} seconds'.format(datetime.timedelta(seconds=round(\ 
          timeit.default_timer() - start_time)))) 
    return model 
 
if __name__ == '__main__': 
    #Create some random training data 
    train_data = np.random.randint(0, 10, 3*512*512*20, dtype='uint8').reshape(-1, 3, 512, 512) 
    train_labels = np.random.randint(0, 1, 7*512*512*20, dtype='uint8').reshape(-1, 512*512, 7) 
    #Get dims of the data 
    data_dims = train_data.shape[2:] 
    data_shape = np.prod(data_dims) 
    #Create initial model 
    initial_model = conv_model((train_data.shape[1], train_data.shape[2], train_data.shape[3]),\ 
                               data_shape, 3, 4, 1, 2, train_labels.shape[-1]) 
    #Train initial model on first part of the training data 
    initial_model.fit(train_data[0:10], train_labels[0:10], verbose=2) 
    #Store initial weights 
    initial_weights = initial_model.get_weights() 
 
    #Create transfer learning model 
    transf_model = conv_model((train_data.shape[1], train_data.shape[2], train_data.shape[3]),\ 
                              data_shape, 3, 4, 1, 2, train_labels.shape[-1], False) 
    #Set transfer model weights 
    transf_model.set_weights(initial_weights) 
    #Set all layers trainable to False (except final conv layer) 
    for layer in transf_model.layers: 
        layer.trainable = False 
    transf_model.layers[9].trainable = True 
    print(transf_model.layers[9]) 
    #Compile model 
    transf_model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=1e-4),\ 
                         metrics=["accuracy"]) 
    #Train model on second part of the data 
    transf_model.fit(train_data[10:20], train_labels[10:20], verbose=2) 
    #Store transfer model weights 
    transf_weights = transf_model.get_weights() 
 
    #Check where the weights have changed 
    for i in range(len(initial_weights)): 
        update_w = np.sum(initial_weights[i] != transf_weights[i]) 
        if update_w != 0: 
            print(str(update_w)+' updated weights for layer '+str(transf_model.layers[i])) 

请您参考如下方法:

一旦你编译了你的模型——你失去了你以前的权重，因为它们被重新采样了。您需要先将它们转移，将权重设置为不可训练，然后再进行编译:

#Compile model 
transf_model.set_weights(initial_weights) 
 
#Set all layers trainable to False (except final conv layer) 
for layer in transf_model.layers: 
    layer.trainable = False 
 
transf_model.layers[9].trainable = True 
 
transf_model.compile(loss="categorical_crossentropy", optimizer=Adam(lr=1e-4),\ 
                     metrics=["accuracy"]) 

否则 - 权重会随着重新采样而改变。

编辑:

模型应该在更改后编译 - 因为在编译期间 keras 正在将所有可训练/不可训练的权重设置在一个列表中，该列表不会进一步更改。