Keras自定义数据生成器提供多输入和多输出的尺寸错误(功能性api模型) [英] Keras custom data generator giving dimension errors with multi input and multi output( functional api model)

问题描述

我已经用Keras编写了一个生成器函数，然后从__getitem__返回X，y之前，我仔细检查了X和Y的形状，它们都可以，但是生成器给出了尺寸不匹配数组和警告.

I have written a generator function with Keras, before returning X,y from __getitem__ I have double check the shapes of the X's and Y's and they are alright, but generator is giving dimension mismatch array and warnings.

(要复制的Colab代码: https://colab.research.google .com/drive/1bSJm44MMDCWDU8IrG2GXKBvXNHCuY70G?usp = sharing )

(Colab Code to reproduce: https://colab.research.google.com/drive/1bSJm44MMDCWDU8IrG2GXKBvXNHCuY70G?usp=sharing)

我的训练和验证生成器与

My training and validation generators are pretty much same as

class ValidGenerator(Sequence):
    def __init__(self, df, batch_size=64):
        self.batch_size = batch_size
        self.df = df
        self.indices = self.df.index.tolist()
        self.num_classes = num_classes
        self.shuffle = shuffle
        self.on_epoch_end()

    def __len__(self):
        return int(len(self.indices) // self.batch_size)

    def __getitem__(self, index):
        index = self.index[index * self.batch_size:(index + 1) * self.batch_size]
        batch = [self.indices[k] for k in index]
        
        X, y = self.__get_data(batch)
        return X, y

    def on_epoch_end(self):
        self.index = np.arange(len(self.indices))
        if self.shuffle == True:
            np.random.shuffle(self.index)

    def __get_data(self, batch):
        #some logic is written here
        #hat prepares 3 X features and 3 Y outputs 
        X = [input_array_1,input_array_2,input_array_3]
        y = [out_1,out_2,out_3]
        #print(len(X))
        
        return X, y

我是X的回音，y分别具有3个输入要素和3个输出要素，所以X的形状为(3,32,10,1)

I am return tupple of X,y from which has 3 input features and 3 output features each, so shape of X is (3,32,10,1)

我正在使用功能性api构建具有以下结构的模型(我具有诸如级联，多输入/输出等功能，而按顺序是不可能的)

I am using functional api to build model(I have things like concatenation, multi input/output, which isnt possible with sequential) with following structure

当我尝试使用以下代码将模型与生成器拟合时

When I try to fit the model with generator with following code

train_datagen = TrainGenerator(df=train_df,  batch_size=32, num_classes=None, shuffle=True)
valid_datagen = ValidGenerator(df=train_df,  batch_size=32, num_classes=None, shuffle=True)
model.fit(train_datagen, epochs=2,verbose=1,callbacks=[checkpoint,es])

我收到了这些警告和错误，这些警告和错误并没有消失

I get these warnings and errors, that dont go away

第1/2集 警告:tensorflow:为输入> Tensor("input_1:0&"; shape =(None，10)，dtype = float32)构造了形状为(None，10)的模型，但在带有不兼容的形状(无，无，无).

Epoch 1/2 WARNING:tensorflow:Model was constructed with shape (None, 10) for input >Tensor("input_1:0", shape=(None, 10), dtype=float32), but it was called >on an input with incompatible shape (None, None, None).

警告:tensorflow:模型的形状为(None，10)，可用于输入 Tensor("input_2:0&"，shape =(None，10)，dtype = float32)，但它是 在形状不兼容的输入(无，无，无)上调用. 警告:tensorflow:模型的形状为(None，10)，用于 输入Tensor("input_3:0&"，shape =(None，10)，dtype = float32)，但它是 在形状不兼容的输入(无，无，无)上调用. ... ... 致电 返回超级(RNN，自我).调用(输入，** kwargs) /home/eduardo/.virtualenvs/kgpu3/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:975 致电 input_spec.assert_input_compatibility(self.input_spec，输入， /home/eduardo/.virtualenvs/kgpu3/lib/python3.8/site-packages/tensorflow/python/keras/engine/input_spec.py:176 assert_input_compatibility 提高ValueError('Input'+ str(input_index)+'层'+

WARNING:tensorflow:Model was constructed with shape (None, 10) for input Tensor("input_2:0", shape=(None, 10), dtype=float32), but it was called on an input with incompatible shape (None, None, None). WARNING:tensorflow:Model was constructed with shape (None, 10) for input Tensor("input_3:0", shape=(None, 10), dtype=float32), but it was called on an input with incompatible shape (None, None, None). ... ... call return super(RNN, self).call(inputs, **kwargs) /home/eduardo/.virtualenvs/kgpu3/lib/python3.8/site-packages/tensorflow/python/keras/engine/base_layer.py:975 call input_spec.assert_input_compatibility(self.input_spec, inputs, /home/eduardo/.virtualenvs/kgpu3/lib/python3.8/site-packages/tensorflow/python/keras/engine/input_spec.py:176 assert_input_compatibility raise ValueError('Input ' + str(input_index) + ' of layer ' +

ValueError: Input 0 of layer lstm is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: [None, None, None, 88]

我已经重新检查了整个代码，并且无法像警告或错误一样输入(无，无，无)，我的输入尺寸是(3,32,10,1)

I have rechecked whole code and it isnt possible to have input (None,None,None) like in warning or in error, my input dimension is (3,32,10,1)

更新

我也试图用python编写一个生成器函数，并且得到了完全相同的错误.

I have also tried to write a generator function with python and got exactly same error.

我的生成器功能

def generate_arrays_from_file(batchsize,df):
    #print(bat)
    inputs = []
    targets = []
    batchcount = 0
    while True:
            
            df3 = df.loc[np.arange(batchcount*batchsize,(batchcount*batchsize)+batchsize)]
            #Some pre processing
            X = [input_array_1,input_array_2,input_array_3]
            y = [out_1,out_2,out_3]
            yield X,y 
            batchcount = batchcount +1

在内部使用keras似乎是错误的(可能是由于我使用的是功能性API)

It seems like it is something wrong internally wit keras (may be due to the fact I am using functional API)

更新2

我也尝试输出元组

       X = (input1_X,input2_X,input3_X)
       y = (output1_y,output2_y,output3_y)

，也命名为输入/输出，但是不起作用

and also named input/output, but it doesnt work

        X =  {"input_1": input1_X, "input_2": input2_X,"input_3": input3_X}
        y = {"output_1": output1_y, "output_2": output2_y,"output_3": output3_y}

有关问题制定的说明:

将单个X要素更改为形状(32,10)而不是(32,10,1)可能有助于摆脱此错误，但这不是我想要的，这改变了我的问题(我不再有10个时间步长各有一个功能)

Changing the individual X features to shape (32,10) instead of (32,10,1) might help to get rid of this error but that is not what I want, it changes my problem(I no longer have 10 time steps with one feature each)

推荐答案

为解决此错误:

ValueError: Input 0 of layer lstm is incompatible with the layer: expected ndim=3, found ndim=4. Full shape received: [None, None, None, 88]

TrainGenerator应该以以下方式更改. 当前代码:

TrainGenerator should be changed in the following way. Current code:

input1_X = np.array(df3['input1_X'].to_list()).reshape(dlen,pad_len,1)
input2_X = np.array(df3['input2_X'].to_list()).reshape(dlen,pad_len,1)
input3_X = np.array(df3['input3_X'].to_list()).reshape(dlen,pad_len,1)

应更改为:

input1_X = np.array(df3['input1_X'].to_list()).reshape(dlen,pad_len)
input2_X = np.array(df3['input2_X'].to_list()).reshape(dlen,pad_len)
input3_X = np.array(df3['input3_X'].to_list()).reshape(dlen,pad_len)

原因是3个输入中的每一个都期望一个2维数组，但是生成器提供3维数组.预期的形状是(batch_size，10).

The reason is that each of the 3 Inputs expects a 2-dimensional array, but the generator provides a 3-dimensional one. The expected shape is (batch_size, 10).

这篇关于Keras自定义数据生成器提供多输入和多输出的尺寸错误(功能性api模型)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！