Typically to perform supervised learning, you need two types of data sets: In one dataset (your "gold standard"), you have the input data together with ... ... <看更多>

In the above case, half the dataset does not contribute to the training of the model! This is not optimal, and can cause problems – especially if the ... ... <看更多>

Validation Sets and Test Sets · Learning objectives · The dataset · Use the right version of TensorFlow · Import relevant modules · Load the datasets from the ... ... <看更多>

Validation Set: this data set is used to minimize overfitting. ... If the accuracy over the training data set increases, but the accuracy over the ... ... <看更多>

The test dataset is the best measure of the network accuracy, and should only be used once, once all training is finished. So I think the issue is that, ... ... <看更多>