Why not change correct_pred to exempt one-hot?

guillaume-chevalier / LSTM-Human-Activity-Recognition

Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst six activity categories - Guillaume Chevalier

MIT License

3.33k stars 935 forks source link

Why not change correct_pred to exempt one-hot? #26

Open KennCoder7 opened 5 years ago

KennCoder7 commented 5 years ago

correct_pred = tf.nn.in_top_k(predictions=pred, targets=y, k=1)