Tensorflow多类分类损失

Question

I've been recently trying to implement a multi-class classification LSTM architecture, based on this example: biLSTM example

After I changed

self.label = tf.placeholder(tf.int32, [None])

to

self.label = tf.placeholder(tf.int32, [None,self.n_class)

The model seems to train normally, yet I am having trouble with this step:

    self.loss = tf.reduce_mean(
        tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y_hat, labels=self.label))

    # prediction
    self.prediction = tf.argmax(tf.nn.softmax(y_hat), 1)

As, even though the model learns normally, the predictions does not seem to work for multiple variables. I was wondering how should one code the self.prediction object, so that it emits a vector of predictions for individual instances?

Thank you very much.

Answer 1

I was wondering how should one code the self.prediction object, so that it emits a vector of predictions for individual instances?

In general tf.nn.softmax returns a vector of probabilities. You just can't see them because your are using tf.argmax , which returns the index of the largest value. Therefore you will just get one number. Just remove tf.argmax and you should be fine.