I have code in Tensorflow using convolution neural network to recognize the characters in street view Text (SVT) data.

Since the label type is string, what should I use instead of tf.nn.sparse_softmax_cross_entropy_with_logits() in the loss function?

I cannot use tf.nn.sparse_softmax_cross_entropy_with_logits() because the labels her must be an int dtype??


The loss function is correct, you just need to convert categorical variables into numerical representations using one-hot vector encoding. Please take a look at this.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.