Keras accuracy does not change

by

The most likely reason is that the optimizer is not suited to your dataset. Here is a list of Keras optimizers from the documentation.

I recommend you first try SGD with default parameter values. If it still doesn’t work, divide the learning rate by 10. Do that a few times if necessary. If your learning rate reaches 1e-6 and it still doesn’t work, then you have another problem.

In summary, replace this line:

model.compile(loss = "categorical_crossentropy", optimizer = "adam")

with this:

from keras.optimizers import SGD
opt = SGD(lr=0.01)
model.compile(loss = "categorical_crossentropy", optimizer = opt)

and change the learning rate a few times if it doesn’t work.

If it was the problem, you should see the loss getting lower after just a few epochs.

More Related Contents:

  1. Deep-Learning Nan loss reasons
  2. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  3. Make a custom loss function in keras
  4. Keras not training on entire dataset
  5. How to apply gradient clipping in TensorFlow?
  6. How does Keras calculate the accuracy?
  7. Keras Sequential model input layer
  8. How to concatenate two layers in keras?
  9. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  10. How to compute Receiving Operating Characteristic (ROC) and AUC in keras?
  11. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  12. ValueError: Error when checking target: expected model_2 to have shape (None, 252, 252, 1) but got array with shape (300, 128, 128, 3)
  13. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  14. Keras import error Nadam
  15. How can I use a pre-trained neural network with grayscale images?
  16. Removing then Inserting a New Middle Layer in a Keras Model
  17. Keras: “RuntimeError: Failed to import pydot.” after installing graphviz and pydot
  18. How to know if underfitting or overfitting is occuring?
  19. memory issues when transforming np.array using to_categorical
  20. Save and load model optimizer state
  21. confusion matrix error “Classification metrics can’t handle a mix of multilabel-indicator and multiclass targets”
  22. What is the role of TimeDistributed layer in Keras?
  23. How does mask_zero in Keras Embedding layer work?
  24. keras: how to save the training history attribute of the history object
  25. Keras, how do I predict after I trained a model?
  26. How to add and remove new layers in keras after loading weights?
  27. ‘Tensor’ object has no attribute ‘lower’
  28. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  29. Can I send callbacks to a KerasClassifier?
  30. Keras give input to intermediate layer and get final output

Leave a Comment