使用multi_gpu_model和layers.trainable = True时,keras微调预训练模型不会改变权重

时间:2018-06-01 23:09:34

标签: python tensorflow keras multi-gpu

我正在加载VGG16预训练模型,添加几个密集层并对基础VGG16的最后5层进行微调。我在mutliple gpus上训练我的模型。我在训练前后保存了模型。尽管有layers.trainable = True,权重是相同的。

请帮忙!

继承代码

    from keras import applications
    from keras import Model
    <import other relevant Keras layers, etc.>


    model = applications.VGG16(weights = "imagenet", include_top = False, input_shape = (224,224,3))

    model.save('./before_training')

    for layer in model.layers:
        layer.trainable = False

    for layer in model.layers[-5:]:
        layer.trainable = True

     x = model.output
     x = Flatten()(x)
     x = Dense(1024, activation = "relu")(x)
     x = Dropout(0.5)(x)
     x = Dense(1024, activation = "relu")(x)
     predictions = Dense(2, activation = "softmax")(x)
     model_final = Model(input = model.input, output = predictions)


     from keras.utils import multi_gpu_model
     parallel_model = multi_gpu_model(model_final, gpus = 4)
     parallel_model.compile(loss = "categorical_crossentropy" ..... )


     datagen = ImageDataGenerator(....)


     early = EarlyStopping(...)

     train_generator = datagen.flow_from_directory(train_data_dir,...)
     validation_generator = datagen.flow_from_directory(test_data_dir,...)

     parallel_model.fit_generator(train_generator, validation_data = valiudation_generator,...)

     model_final.save('./after_training)

before_training和after_training模型中的权重相同!!!这不是我的预期!

0 个答案:

没有答案