1

我正在建立一个模型，它有一个图像输入 (130,130,1) 和 3 个输出，每个输出包含一个 (10,1) 向量，其中单独应用了 softmax。

（受 J. Goodfellow、Yaroslav Bulatov、Julian Ibarz、Sacha Arnoud 和 Vinay D. Shet 的启发。使用深度卷积神经网络从街景图像中识别多位数字。CorR，abs/1312.6082，2013。URL http:// arxiv.org/abs/1312.6082，遗憾的是他们没有发布他们的网络）。

input = keras.layers.Input(shape=(130,130, 1)
l0 = keras.layers.Conv2D(32, (5, 5), padding="same")(input)
[conv-blocks etc]
l12 = keras.layers.Flatten()(l11)
l13 = keras.layers.Dense(4096, activation="relu")(l12)
l14 = keras.layers.Dense(4096, activation="relu")(l13)
output1 = keras.layers.Dense(10, activation="softmax")(l14)
output2 = keras.layers.Dense(10, activation="softmax")(l14)
output3 = keras.layers.Dense(10, activation="softmax")(l14)

model = keras.models.Model(inputs=input, outputs=[output1, output2, output3])
model.compile(loss=['categorical_crossentropy', 'categorical_crossentropy', 
              'categorical_crossentropy'],
              loss_weights=[1., 1., 1.],
              optimizer=optimizer,
              metrics=['accuracy'])

train_generator = train_datagen.flow(x_train,
              [[y_train[:, 0, :], y_train[:, 1, :], y_train[:, 2, :]], 
              batch_size=batch_size)

但后来我得到：ValueError: x(images tensor) 和y(labels) 应该有相同的长度。找到：x.shape = (1000, 130, 130, 1), y.shape = (3, 1000, 10)

但是，如果我将其更改为：

 [same as before]
 train_generator = train_datagen.flow(x_train,
              y_train, 
              batch_size=batch_size)

Then i'm getting: ValueError: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 3 array(s)

  • dimension(x_train) = (1000, 130, 130, 1)
    • where each single image is (130, 130, 1) and there are 1000 images
  • dimension(y_train) = (1000, 3, 10)

In the documentation it is stated that it should be like that;

model = Model(inputs=[main_input, auxiliary_input], outputs= 
[main_output, auxiliary_output])

However, I don't know how you should be able to have the same length for outputs and inputs?

4

1 回答 1

0

Thanks to @Djib2011. When I looked up examples in the documentation for passing it in a dictionary, I remarked that all the examples make use of model.fit() and not model.fit_generator().

所以我做了研究，发现 ImageDataGenerator 仍然存在一个错误（自 2016 年以来开放！），具有单输入和多输出。悲剧。

所以解决方案是使用model.fit()而不是model.fit_generator().

于 2019-06-24T06:50:07.390 回答