代码之家 › 专栏 › 技术社区 › George

应在至少包含2个输入的列表上调用“Concatenate”层`

tensorflow2.0 deep-learning keras machine-learning python-3.x

0

George · 技术社区 · 4 年前

我创建了一个模型,它接受一个输入层,并生成两个输出层。

 model = Model(inputs=efficient_net.input, outputs=[reg_pred, class_pred])

我正在训练模型,接收结果并将模型的2个实例保存为两个实例。h5档案。

model_weights = []
for item in os.listdir(packages_root):
    if ".h5" in item:
        model_weights.append(item)

所以,我有 ['model_2.h5', 'model_1.h5']

def ensemble(models, model_input):
    
    Models_output = [model(model_input) for model in models]
    Avg = Average()(Models_output)
    
    ensemble = Model(inputs=model_input, outputs=Avg, name='ensemble')
    ensemble.summary()
    ensemble.compile(Adam(lr=.0001), loss=loss, metrics=metrics)
    
    return ensemble

那么我会:

model_input = Input(shape=models[0].input_shape[1:])

其中: <KerasTensor: shape=(None, 32, 32, 3) dtype=float32 (created by layer 'input_12')>

ensemble_model = ensemble(models, model_input)

这给了我:

ValueError: A merge layer should be called on a list of inputs.

Avg = Average()(Models_output) .

因此,我试图做到:

def ensemble(models, model_input):
    
    Models_output = []
    for model in models:
        Models_output.append(model(model_input))
        
    # Concatenate the 2 output layers
    Conc = Concatenate()([Models_output[0], Models_output[1])
    Avg = Average()(Conc)
    
    ensemble = Model(inputs=model_input, outputs=Avg, name='ensemble')
    ensemble.summary()
    ensemble.compile(Adam(lr=.0001), loss=loss, metrics=metrics)
    
    return ensemble

现在我知道了:

ValueError: A 连接 layer should be called on a list of at least 2 inputs

print(Models_output) ,提供:

[[<KerasTensor: shape=(None, 4) dtype=float32 (created by layer 'model_1')>, <KerasTensor: shape=(None, 2) dtype=float32 (created by layer 'model_1')>],

 [<KerasTensor: shape=(None, 4) dtype=float32 (created by layer 'model_2')>, <KerasTensor: shape=(None, 2) dtype=float32 (created by layer 'model_2')>]]

0 回复 | 直到 4 年前

1

Marco Cerliani 4 年前

错误是因为您调用了 Average reg_pred , class_pred ).

平均的

这里是一个虚拟示例,其中我们拟合2个模型以产生2个输出:

X = np.random.uniform(0,1, (64,28,28,1))
y = np.random.randint(0,2, 64)

def get_model():
    inp = Input((28,28,1))
    reg_pred = Dense(1)(inp)
    class_pred = Dense(2, activation='softmax')(Flatten()(inp))
    model = Model(inp, [reg_pred, class_pred])
    model.compile('adam', ['mse', 'sparse_categorical_crossentropy'])
    return model

model1 = get_model()
model1.fit(X,[X,y])
model2 = get_model()
model2.fit(X,[X,y])

您的集成函数会产生错误:

def ensemble(models, model_input):
    
    Models_output = [model(model_input) for model in models]
    Avg = Average()(Models_output)
    
    ensemble = Model(inputs=model_input, outputs=Avg, name='ensemble')
    ensemble.compile('adam', ['mse', 'sparse_categorical_crossentropy'])
    
    return ensemble

model_input = Input((28,28,1))
models = [model1, model2]
model_ensemble = ensemble(models, model_input)

def ensemble(models, model_input):
    
    output_reg = []
    output_class = []
    for model in models:
        out_reg, out_class = model(model_input)
        output_reg.append(out_reg)
        output_class.append(out_class)
    avg_reg = Average()(output_reg)
    avg_class = Average()(output_class)
    
    ensemble = Model(inputs=model_input, outputs=[avg_reg, avg_class], name='ensemble')
    ensemble.compile('adam', ['mse', 'sparse_categorical_crossentropy'])
    
    return ensemble

model_input = Input((28,28,1))
models = [model1, model2]
model_ensemble = ensemble(models, model_input)