tensorflow: Keras custom data generator giving dimension errors with multi input and multi output( functional api model)

System information

• OS Platform and Distribution (e.g., Linux Ubuntu 20.04 and Colab):
• TensorFlow installed from; Pip3 install …
• Tensorflow version: v2.3.0-54-gfcc4b966f1 2.3.1

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

Note: I have updated the issue at the end as well.

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.

I suspect that the problem is relating multiple input, which is being cosidered one by the input layer of tf.keras. Each input features is of shape (32,10,1) but yielding [input_array_1,input_array_2,input_array_3] makes it (3,32,10,1)

My training and validation generators are pretty musch 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

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

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

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])

I get these warnings and errors, that dont go away

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).

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]

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)

Update

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

My generator function

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

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

Update 2

I also tried to output tuple

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

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}

Note about problem formulation:

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)