时间戳

首页 > 解决方案 > Keras微调InceptionV3张量维度误差

python - Keras微调InceptionV3张量维度误差

问题描述

我正在尝试在 Keras 中微调模型：

    inception_model = InceptionV3(weights=None, include_top=False, input_shape=(150, 
150, 1))

    x = inception_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(256, activation='relu', name='fc1')(x)
    x = Dropout(0.5)(x)
    predictions = Dense(10, activation='softmax', name='predictions')(x)
    classifier = Model(inception_model.input, predictions)


    ####training training training ... save weights


    classifier.load_weights("saved_weights.h5")
  
    classifier.layers.pop()
    classifier.layers.pop()
    classifier.layers.pop()
    classifier.layers.pop()
    ###enough poping to reach standard InceptionV3 

    x = classifier.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(256, activation='relu', name='fc1')(x)
    x = Dropout(0.5)(x)
    predictions = Dense(10, activation='softmax', name='predictions')(x)
    classifier = Model(classifier.input, predictions)

但我得到了错误：

ValueError: Input 0 is incompatible with layer global_average_pooling2d_3: expected ndim=4, found ndim=2

标签： pythonmachine-learningkerasdeep-learning

解决方案

您不应该 pop()在使用功能 API（即keras.models.Model）创建的模型上使用方法。只有顺序模型（即keras.models.Sequential）具有内置pop()方法（用法：model.pop()）。相反，使用索引或图层名称来访问特定图层：

classifier.load_weights("saved_weights.h5")
x = classifier.layers[-5].output   # use index of the layer directly
x = GlobalAveragePooling2D()(x)

推荐阅读