Error when checking model input: expected convolution2d_input_1 to have 4 dimensions, but got array with shape (32, 32, 3)

by

The input shape you have defined is the shape of a single sample. The model itself expects some array of samples as input (even if its an array of length 1).

Your output really should be 4-d, with the 1st dimension to enumerate the samples. i.e. for a single image you should return a shape of (1, 32, 32, 3).

You can find more information here under “Convolution2D”/”Input shape”

Edit: Based on Danny’s comment below, if you want a batch size of 1, you can add the missing dimension using this:

image = np.expand_dims(image, axis=0)

More Related Contents:

  1. Keras input explanation: input_shape, units, batch_size, dim, etc
  2. How do I get the weights of a layer in Keras?
  3. Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?
  4. Keras Dense layer’s input is not flattened
  5. Keras Sequential model input layer
  6. When does keras reset an LSTM state?
  7. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  8. Specify connections in NN (in keras)
  9. how to format the image data for training/prediction when images are different in size?
  10. How to calculate optimal batch size
  11. Keras Text Preprocessing – Saving Tokenizer object to file for scoring
  12. Keras custom loss function: Accessing current input pattern
  13. How to speed up Gensim Word2vec model load time?
  14. What is the role of TimeDistributed layer in Keras?
  15. What’s the difference between “hidden” and “output” in PyTorch LSTM?
  16. Multiple outputs in Keras
  17. Can Keras deal with input images with different size?
  18. How to implement Grad-CAM on a trained network
  19. Keras split train test set when using ImageDataGenerator
  20. keras: how to save the training history attribute of the history object
  21. How to add and remove new layers in keras after loading weights?
  22. What is the difference between Keras model.evaluate() and model.predict()?
  23. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  24. How to display custom images in TensorBoard using Keras?
  25. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  26. How do I plot a Keras/Tensorflow subclassing API model?
  27. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  28. Keras give input to intermediate layer and get final output
  29. Multi-input Multi-output Model with Keras Functional API
  30. how to implement custom metric in keras?

Leave a Comment