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

Question

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.

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

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

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)

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)

Have you tried with run_eagerly=True in model.compile. That may solve your issue. — sreagm
– sreagm, Commented Nov 23, 2020 at 11:33

Andrey · Accepted Answer · 2020-11-13 11:13:42Z

0

Keras use 'None' for dynamic dimensions.

As you can see on the model.summary() chart - the model expecting shape(None, 10) for all of your inputs, which is two dimensional. With batch dimension - you should feed three dimensional data to the model.

But you are feeding four dimensional data.

I would guess that your model doesn't split your input list by three inputs. Try to change your inputs to tuple:

    X = (input_array_1,input_array_2,input_array_3)

answered Nov 13, 2020 at 11:13

Andrey

6,6393 gold badges24 silver badges51 bronze badges

Sign up to request clarification or add additional context in comments.

6 Comments

Andrey Over a year ago

Why the last dimension of your data is 1 ? The model expecting 10

A.B Over a year ago

Thankyou for the answer, I just tried, but didnt help. I have exactly the same errors

A.B Over a year ago

32 is my batch, 10 is time step and 1 is no of features

Andrey Over a year ago

you have to change your model then - it is expecting 10 instead of 1 at the last dim

Andrey Over a year ago

or just squeeze the last dim of your data

|

Oleg · Accepted Answer · 2021-01-11 18:26:42Z

0

In order to resolve this error:

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 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)

Should be changed to:

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)

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).

answered Jan 11, 2021 at 18:26

Oleg

212 bronze badges

1 Comment

A.B Over a year ago

I have many-to-one architecture where I have 10 time steps and i predict next one. The change you suggested will take away all the benefit of sequential prediction as it will make data one time step with 10 featurs (dlen,10), which should be (dlen,10,1)

BestDogeStackoverflow · Accepted Answer · 2021-12-01 08:13:08Z

I had a similar issue with a custom generator that just had to pass a numpy array of size 10 as input and one single output.

To solve this problem i had to trasform the shape of the 2 vectors passed to the neural network like this:

def slides_generator(integer_list):
    
    # stuff happens

    x = np_ts[np_index:np_index+10] # numpy array
    y = np_ts[np_index+10] # numpy array

    yield tf.convert_to_tensor(x)[np.newaxis, ...], tf.convert_to_tensor(y)[np.newaxis, ...]
    
doge_gen = slides_generator(integer_list) #next(doge_gen)

basically you need to pass the 2 arrays with shape (None,size), so in my case were (None,10) and (None,1), and to achieve this i just passed 2 reshaped tensors.

you need the None dimension as the batch size.

Collectives™ on Stack Overflow

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

3 Answers 3

6 Comments

1 Comment

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

6 Comments

1 Comment

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related