Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’

by

By default, Convolution2D (https://keras.io/layers/convolutional/) expects the input to be in the format (samples, rows, cols, channels), which is “channels-last”. Your data seems to be in the format (samples, channels, rows, cols). You should be able to fix this using the optional keyword data_format="channels_first" when declaring the Convolution2D layer.

model.add(Convolution2D(32, (3, 3), activation='relu', input_shape=(1,28,28), data_format="channels_first"))

More Related Contents:

  1. Keras Dense layer’s input is not flattened
  2. Keras + Tensorflow and Multiprocessing in Python
  3. Loading a trained Keras model and continue training
  4. How do I check if keras is using gpu version of tensorflow?
  5. How do I get the weights of a layer in Keras?
  6. Multiple outputs in Keras
  7. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  8. Keras give input to intermediate layer and get final output
  9. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  10. Keras, How to get the output of each layer?
  11. How do you create a custom activation function with Keras?
  12. Deep-Learning Nan loss reasons
  13. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  14. Why is TensorFlow 2 much slower than TensorFlow 1?
  15. How to assign a value to a TensorFlow variable?
  16. NaN loss when training regression network
  17. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  18. What is the difference between tf.keras and tf.python.keras?
  19. Keras custom loss function: Accessing current input pattern
  20. How does Keras handle multilabel classification?
  21. Unknown initializer: GlorotUniform when loading Keras model
  22. How to use fit_generator with multiple inputs
  23. How to implement Grad-CAM on a trained network
  24. keras: how to save the training history attribute of the history object
  25. How to add and remove new layers in keras after loading weights?
  26. Unexpected keyword argument ‘ragged’ in Keras
  27. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  28. Can I send callbacks to a KerasClassifier?
  29. Invalid Argument Error / Graph Execution Error
  30. how to implement custom metric in keras?

Leave a Comment