What’s the difference between sparse_softmax_cross_entropy_with_logits and softmax_cross_entropy_with_logits?

by

Having two different functions is a convenience, as they produce the same result.

The difference is simple:

  • For sparse_softmax_cross_entropy_with_logits, labels must have the shape [batch_size] and the dtype int32 or int64. Each label is an int in range [0, num_classes-1].
  • For softmax_cross_entropy_with_logits, labels must have the shape [batch_size, num_classes] and dtype float32 or float64.

Labels used in softmax_cross_entropy_with_logits are the one hot version of labels used in sparse_softmax_cross_entropy_with_logits.

Another tiny difference is that with sparse_softmax_cross_entropy_with_logits, you can give -1 as a label to have loss 0 on this label.

More Related Contents:

  1. How to choose cross-entropy loss in TensorFlow?
  2. What is the meaning of the word logits in TensorFlow? [duplicate]
  3. What does tf.nn.conv2d do in tensorflow?
  4. How to count total number of trainable parameters in a tensorflow model?
  5. should I use float or classes as output for the final layer in my neural network?
  6. How to make a custom activation function with only Python in Tensorflow?
  7. Keras input explanation: input_shape, units, batch_size, dim, etc
  8. Test labels for regression caffe, float not allowed?
  9. Keras + Tensorflow and Multiprocessing in Python
  10. How to assign a value to a TensorFlow variable?
  11. Tensorflow: How to replace or modify gradient?
  12. What is the difference between a sigmoid followed by the cross entropy and sigmoid_cross_entropy_with_logits in TensorFlow?
  13. How to calculate the number of parameters for convolutional neural network?
  14. What are the differences between all these cross-entropy losses in Keras and TensorFlow?
  15. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  16. caffe data layer example step by step
  17. Loading a trained Keras model and continue training
  18. How do I check if keras is using gpu version of tensorflow?
  19. What is the purpose of the add_loss function in Keras?
  20. Pytorch, what are the gradient arguments
  21. Multiple outputs in Keras
  22. Tensor is not an element of this graph
  23. Tensorflow : Memory leak even while closing Session?
  24. scale the loss value according to “badness” in caffe
  25. Why use softmax as opposed to standard normalization?
  26. In Keras, what exactly am I configuring when I create a stateful `LSTM` layer with N `units`?
  27. What is right batch normalization function in Tensorflow?
  28. caffe: model definition: write same layer with different phase using caffe.NetSpec()
  29. 2-D convolution as a matrix-matrix multiplication [closed]
  30. Choosing number of Steps per Epoch

Leave a Comment