search

pumpikano / tf-dann

Domain-Adversarial Neural Network in Tensorflow
MIT License
628 stars 224 forks source link

How to compute prediction and transformed features? #6

Closed saadirtza closed 7 years ago

saadirtza commented 7 years ago

Hi Pumpikano,

thanks for answering my questions. i am trying to get the prediction values instead of predicted labels and accuracy, in this regard, i have modify the code as Changed the line correct_label_pred = tf.equal(tf.argmax(model.classify_labels, 1), tf.argmax(model.pred, 1)) to label_acc_lk = model.pred

i am getting the predictions, just wondering is it correct to do so?

Many thanks

Regards Saad

pumpikano commented 7 years ago

I don't understand your question.

model.pred is the softmax outputs, tf.argmax(model.pred, 1) would give you the highest probability label, and correct_label_pred tells you which predictions are correct.

saadirtza commented 7 years ago

Thanks Pumpikano.. i understand now..

Regards