Keras 函数 API 多输入形状错误

Question

我的目标是使用 CNN 遍历图片，然后在密集层之前添加一组额外数据。

picIn = keras.Input(shape=x[0].shape)
conv1 = layers.Conv2D(32,kernel_size=3,padding='same',use_bias=False)(picIn)
batch1 = layers.BatchNormalization()(conv1)
leaky1 = layers.LeakyReLU(alpha=.3)(batch1)
conv2 = layers.Conv2D(32,kernel_size=3,padding='same',use_bias=False)(leaky1)
batch2 = layers.BatchNormalization()(conv2)
leaky2 = layers.LeakyReLU(alpha=.3)(batch2)
cdrop1 = layers.Dropout(.20)(leaky2)
conv3= layers.Conv2D(64,kernel_size=3,padding='same',use_bias=False)(cdrop1)
batch3 = layers.BatchNormalization()(conv3)
leaky3 = layers.LeakyReLU(alpha=.3)(batch3)
conv4 = layers.Conv2D(64,kernel_size=3,padding='same',use_bias=False)(leaky3)
batch4 = layers.BatchNormalization()(conv4)
leaky4 = layers.LeakyReLU(alpha=.3)(batch4)
cdrop2 = layers.Dropout(.20)(leaky4)
flat1 = layers.Flatten()(cdrop2)

rtheta1 = rtheta[trainCut]
rtheta1 = rtheta1.reshape(467526,1)
rtheta2 = rtheta[testCut]
rtheta2 = rtheta2.reshape(82247,1)

ip2 = keras.Input(shape=rtheta1.shape)
flat2 = layers.Flatten()(ip2)

merge = layers.Concatenate()([flat1,flat2])
hidden1 = layers.Dense(512,use_bias=False)(merge)
batch5 = layers.BatchNormalization()(hidden1)
leaky5 = layers.LeakyReLU(alpha=.3)(batch5)
ddrop1 = layers.Dropout(.20)(leaky5)
hidden2 = layers.Dense(512,use_bias=False)(ddrop1)
batch6 = layers.BatchNormalization()(hidden2)
leaky6 = layers.LeakyReLU(alpha=.3)(batch6)
ddrop2 = layers.Dropout(.20)(leaky6)
hidden3 = layers.Dense(512,use_bias=False)(merge)
batch7 = layers.BatchNormalization()(hidden1)
leaky7 = layers.LeakyReLU(alpha=.3)(batch5)
ddrop3 = layers.Dropout(.20)(leaky5)
output = layers.Dense(1)(ddrop3)
model = keras.Model(inputs = [picIn,ip2], outputs = output)

H = model.fit(x =[ x[trainCut],rtheta[trainCut]],y= y[trainCut],batch_size=args.bsize,validation_data=([x[testCut],rtheta[testCut]], y[testCut]),epochs=args.epochs)

我总是收到与输入形状相关的错误

密集层的输入 0 与该层不兼容：预期输入形状的轴 -1 的值为 473926，但收到的输入形状为 [None、6401]

模型是用形状 (None, 467526, 1) 为输入 Tensor("input_2:0", shape=(None, 467526 , 1), dtype=float32), 但它是在形状不兼容的输入上调用的 (None, 1, 1).

我不知道该做什么。 x[traincut] 是一个大小为 (467526,10,10,2) 的矩阵 rtheta1 是 (467526,1) 也是 y[traincut]

验证数据相同，只是它是 82247 而不是 467526。

我已经试过了，在 ip2 之后没有扁平化，我得到了一个不同的错误，但我认为核心问题仍然是一样的。

如有任何帮助，我们将不胜感激。谢谢！

编辑：显然，数据的形状不正确，但我想出了解决方法。

Answer 1

在将训练数据放入第一个张量之前，您是否确保所有训练数据的形状都是统一的？

Keras 函数 API 多输入形状错误

Keras Functional API Multiple Input Shape Errors

concatenation

flatten

deep-learning

keras

tensorflow