Python Deep Learning Projects

Evaluation of the RNN model

Let's look at our results. Once the model is trained, we can feed the test data that we prepared earlier in this chapter and evaluate the predictions. In this case, we will use a few different metrics to evaluate our model: precision, recall, and F1-scores. 

To evaluate your model, it is important to choose the right kind of metrics—F1-scores are considered more practical compared to the accuracy score.

Some key points to help you understand them in simple terms are as follows:

• Accuracy: The count of correct predictions, divided by the count of total examples that have been evaluated.
• Precision: High precision means you identified nearly all positives appropriately; a low precision score means you often incorrectly ...