I'm training this simple network with a few points, but it can't train. The model looks okay, but when training it raises a ValueError about the dimension of the training data sets. Could someone help? Thanks in advance.

The code is;

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LocallyConnected1D

# Generate random training data
X_train = np.random.rand(1000, 100, 1)
y_train = np.random.randint(0, 10, size=(1000, 1))

# Generate random testing data
X_test = np.random.rand(100, 100, 1)
y_test = np.random.randint(0, 10, size=(100, 1))

# Create a sequential model
model = Sequential()

# Add a LocallyConnected1D layer with 32 filters, a kernel size of 3, and a ReLU activation function
model.add(LocallyConnected1D(32, 3, activation='relu', input_shape=(100, 1)))

# Add a dense layer with 10 units and a softmax activation function
model.add(Dense(10, activation='softmax'))

# Compile the model with categorical cross-entropy loss and Adam optimizer
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

# Train the model on the training data
model.fit(X_train, y_train, epochs=10, batch_size=32, validation_data=(X_test, y_test))

# Evaluate the model on the testing data
test_loss, test_acc = model.evaluate(X_test, y_test)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)

and the ValueError raised is:

ValueError: in user code:

    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\training.py", line 1160, in train_function  *
        return step_function(self, iterator)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\training.py", line 1146, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\training.py", line 1135, in run_step  **
        outputs = model.train_step(data)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\training.py", line 994, in train_step
        loss = self.compute_loss(x, y, y_pred, sample_weight)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\training.py", line 1052, in compute_loss
        return self.compiled_loss(
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\engine\compile_utils.py", line 265, in __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\losses.py", line 152, in __call__
        losses = call_fn(y_true, y_pred)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\losses.py", line 272, in call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\losses.py", line 1990, in categorical_crossentropy
        return backend.categorical_crossentropy(
    File "C:\ProgramData\Anaconda3\envs\tf\lib\site-packages\keras\backend.py", line 5529, in categorical_crossentropy

    ValueError: Shapes (None, 1) and (None, 98, 10) are incompatible
  • $\begingroup$ The architecture seems off. The first layer converts your (100, 1) input in size (98, 32) , and the dense layer than converts it to (98, 10) . And then the network struggle to convert it to your 1 dimensional output. You need to reduce the dimension of your working spaces (via reshape or maxPool1D I think) $\endgroup$
    – Ubikuity
    May 3 at 10:41

1 Answer 1


To elaborate on Ubikuity's comment, there are a couple of issues. The error that you are seeing is because your model output shape is (None, 98, 10), so it will output a 2d tensor. The y_train shape that it is trying to compare against is (1000,1), so they are incompatible. You can specify y_train and y_test to be 1d by simply omitting the last size dimension:

y_train = np.random.randint(0, 10, size=(1000, ))
y_test = np.random.randint(0, 10, size=(100, ))

The second issue is that the output of your LocallyConnected1D layer fed into a Dense layer will have an output of shape (None, 98, 10). An easy fix is to flatten the output of the LocallyConnected1D layer before the Dense layer:


Then your model output shape will be (None, 10), so you can either add a final Dense layer with a single output, or else change your existing final Dense layer to a single output, or reshape your targets to be size=(100,10).

model.add(Dense(10, activation='softmax'))
model.add(Dense(1, activation='softmax'))

or else instead of 1D inputs previously mentioned, do something like :

y_train = np.random.randint(0, 10, size=(1000, 10))
y_test = np.random.randint(0, 10, size=(100, 10))

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.