Keras微调InceptionV3张量尺寸误差 [英] Keras fine-tuning InceptionV3 tensor dimension error
本文介绍了Keras微调InceptionV3张量尺寸误差的处理方法,对大家解决问题具有一定的参考价值,需要的朋友们下面随着小编来一起学习吧!
问题描述
我正在尝试在Keras中微调模型:
I am trying to fine-tune a model in Keras:
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)
但是我得到了错误:
ValueError: Input 0 is incompatible with layer global_average_pooling2d_3: expected ndim=4, found ndim=2
推荐答案
您不应该使用 pop()
使用功能性API创建的模型的方法(即 keras.models.Model
)。只有顺序模型(即 keras.models.Sequential
)具有内置的 pop()
方法(用法: model .pop()
)。而是使用索引或图层名称访问特定图层:
You shouldn't use pop()
method on models created using functional API (i.e. keras.models.Model
). Only Sequential models (i.e. keras.models.Sequential
) have a built-in pop()
method (usage: model.pop()
). Instead, use index or the names of the layers to access a specific layer:
classifier.load_weights("saved_weights.h5")
x = classifier.layers[-5].output # use index of the layer directly
x = GlobalAveragePooling2D()(x)
这篇关于Keras微调InceptionV3张量尺寸误差的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!
查看全文