Keras误解了训练数据的形状 [英] Keras misinterprets training data shape

问题描述

我的训练数据的格式为(?，15)其中?是可变长度.

My training data has the form (?,15) where ? is a variable length.

在创建模型时，我指定以下内容:

When creating my model I specify this:

inp = Input(shape=(None,15))
conv = Conv1D(32,3,padding='same',activation='relu')(inp)
...

我的训练数据的形状为(35730，?，15).

My training data has the shape (35730,?,15).

在python中进行检查，我得到:

Checking this in python I get:

X.shape

输出:(35730，)

Outputs: (35730,)

X[0].shape

输出:(513，15)

Outputs: (513, 15)

当我尝试将模型拟合到训练数据上时，出现ValueError:

When I try to fit my model on my training data I get the ValueError:

Error when checking input: expected input_1 to have 3 dimensions, but got array with shape (35730, 1)

我只能通过在单个样本上使用model.train_on_batch()来训练模型.

I can only train my model by using model.train_on_batch() on a single sample.

我该如何解决?似乎keras认为我的输入数据的形状实际上是(35730，?，15)时的形状是(35730，1)

How can I solve this? It seems like keras thinks the shape of my input data is (35730, 1) when it actually is (35730, ?, 15)

这是keras中的错误还是我做错了什么?

Is this a bug in keras or did I do something wrong?

如果重要的话，我正在使用tensorflow后端.这是keras 2

I am using the tensorflow backend if that matters. This is keras 2

推荐答案

(根据OP对这个问题的评论进行了编辑，他们在其中发布了此链接:

(Edited, according to OP's comment on this question, where they posted this link: https://github.com/fchollet/keras/issues/1920)

您的X不是单个numpy数组，而是一个数组数组. (否则，其形状将为X.shape=(35730,513,15).

Your X is not a single numpy array, it's an array of arrays. (Otherwise its shape would be X.shape=(35730,513,15).

对于fit方法，它必须是单个numpy数组.由于长度是可变的，因此无法拥有包含所有数据的单个numpy数组，因此必须将其划分为较小的数组，每个数组包含的数据长度均相同.

It must be a single numpy array for the fit method. Since you have a variable length, you cannot have a single numpy array containing all your data, you will have to divide it in smaller arrays, each array containing data with the same length.

为此，您应该按形状创建字典，然后手动循环字典(可能还有其他更好的方法...):

For that, you should maybe create a dictionary by shape, and loop the dictionary manually (there may be other better ways to do this...):

#code in python 3.5
xByShapes = {}
yByShapes = {}
for itemX,itemY in zip(X,Y):
    if itemX.shape in xByShapes:
        xByShapes[itemX.shape].append(itemX)
        yByShapes[itemX.shape].append(itemY)
    else:
        xByShapes[itemX.shape] = [itemX] #initially a list, because we're going to append items
        yByShapes[itemX.shape] = [itemY]

最后，您循环这本词典进行培训:

At the end, you loop this dictionary for training:

for shape in xByShapes:
    model.fit(
              np.asarray(xByShapes[shape]), 
              np.asarray(yByShapes[shape]),...
              )

---

掩盖

或者，您可以填充数据，以使所有样本都具有相同的长度(使用零或一些虚拟值).

---

Masking

Alternatively, you can pad your data so all samples have the same length, using zeros or some dummy value.

然后在模型中的任何内容之前，可以添加一个Masking层，该层将忽略这些填充的段. (警告:某些类型的图层不支持遮罩)

Then before anything in your model you can add a Masking layer that will ignore these padded segments. (Warning: some types of layer don't support masking)

这篇关于Keras误解了训练数据的形状的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！