machine-learning - 在keras中整合resnet50和densitynet121

我想做一个resnet50和desnsenet121的合奏，但是出错了：

图表已断开连接：无法在“ input_8”层获取张量Tensor（“ input_8：0”，shape =（?, 224、224、3），dtype = float32）的值。顺利访问了以下先前的层：[]

下面是我的合奏代码：

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)

我以为原因是当我结合使用reset50和densitynet121时，即使我将输入形状设为相同，它们也具有自己的输入层。不同的输入层会导致冲突。那只是我的猜测，我不确定如何解决

最佳答案

创建基本模型时可以设置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，基本模型将使用提供的model_input张量，而不是自己创建单独的输入张量。

关于machine-learning - 在keras中整合resnet50和densitynet121，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/49136762/