Keras: model.evaluate vs model.predict accuracy difference in multi-class NLP task

by

I have found the problem. metrics=['accuracy'] calculates accuracy automatically from cost function. So using binary_crossentropy shows binary accuracy, not categorical accuracy. Using categorical_crossentropy automatically switches to categorical accuracy and now it is the same as calculated manually using model1.predict(). Yu-Yang was right to point out the cost function and activation function for multi-class problem.

P.S: One can get both categorical and binary accuracy by using metrics=['binary_accuracy', 'categorical_accuracy']

More Related Contents:

  1. Why binary_crossentropy and categorical_crossentropy give different performances for the same problem?
  2. Many to one and many to many LSTM examples in Keras
  3. How to calculate optimal batch size
  4. What is the difference between loss function and metric in Keras? [duplicate]
  5. Keras Text Preprocessing – Saving Tokenizer object to file for scoring
  6. ResNet: 100% accuracy during training, but 33% prediction accuracy with the same data
  7. Is deep learning bad at fitting simple non linear functions outside training scope (extrapolating)?
  8. Can Keras deal with input images with different size?
  9. What is the difference between Keras model.evaluate() and model.predict()?
  10. What function defines accuracy in Keras when the loss is mean squared error (MSE)?
  11. Common causes of nans during training of neural networks
  12. Keras Sequential model input layer
  13. How to interpret MSE in Keras Regressor
  14. Intuitive understanding of 1D, 2D, and 3D convolutions in convolutional neural networks [closed]
  15. Epoch vs Iteration when training neural networks [closed]
  16. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  17. What is `weight_decay` meta parameter in Caffe?
  18. Calculate the output size in convolution layer [closed]
  19. Removing then Inserting a New Middle Layer in a Keras Model
  20. multi-layer perceptron (MLP) architecture: criteria for choosing number of hidden layers and size of the hidden layer? [closed]
  21. What is the role of TimeDistributed layer in Keras?
  22. TimeDistributed(Dense) vs Dense in Keras – Same number of parameters
  23. Fine Tuning of GoogLeNet Model
  24. How to create caffe.deploy from train.prototxt
  25. Keras, Tensorflow : Merge two different model output into one
  26. How to reduce a fully-connected (`”InnerProduct”`) layer using truncated SVD
  27. keras: how to save the training history attribute of the history object
  28. Using pre-trained word2vec with LSTM for word generation
  29. How can I get biases from a trained model in Keras?
  30. Choosing number of Steps per Epoch

Leave a Comment