machine-learning - 在keras中集成resnet50和densenet121

Question

我想做 resnet50 和 desnsenet121 的集成，但出现错误:

图已断开连接:无法获取层“input_8”处的张量 Tensor("input_8:0", shape=(?, 224, 224, 3), dtype=float32) 的值。访问之前的以下层没有出现问题:[]

下面是我的集成代码:

from keras import applications
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from keras.models import Model, Input
#from keras.engine.topology import Input
from keras.layers import Average

def resnet50():
    base_model = applications.resnet50.ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
    last = base_model.output
    x = Flatten()(last)
    x = Dense(2000, activation='relu')(x)
    preds = Dense(200, activation='softmax')(x)
    model = Model(base_model.input, preds)
    return model

def densenet121():
    base_model = applications.densenet.DenseNet121(weights='imagenet', include_top=False, input_shape=(224,224, 3))
    last = base_model.output
    x = Flatten()(last)
    x = Dense(2000, activation='relu')(x)
    preds = Dense(200, activation='softmax')(x)
    model = Model(base_model.input, preds)
    return model

resnet50_model = resnet50()
densenet121_model = densenet121()
ensembled_models = [resnet50_model,densenet121_model]
def ensemble(models,model_input):
    outputs = [model.outputs[0] for model in models]
    y = Average()(outputs)
    model = Model(model_input,y,name='ensemble')
    return model

model_input = Input(shape=(224,224,3))
ensemble_model = ensemble(ensembled_models,model_input)

我认为原因是当我组合reset50和densenet121时，它们有自己的输入层，即使我使输入形状相同。不同的输入层会导致冲突。这只是我的猜测，我不知道如何解决它

Answer 1

您可以在创建基础模型时设置input_tensor=model_input。

def resnet50(model_input):
    base_model = applications.resnet50.ResNet50(weights='imagenet', include_top=False, input_tensor=model_input)
    # ...

def densenet121(model_input):
    base_model = applications.densenet.DenseNet121(weights='imagenet', include_top=False, input_tensor=model_input)
    # ...

model_input = Input(shape=(224, 224, 3))
resnet50_model = resnet50(model_input)
densenet121_model = densenet121(model_input)

然后，基础模型将使用提供的 model_input 张量，而不是创建自己的单独输入张量。