This week I focused on finishing the design review presentation and report. I worked on the text emotion recognition portion of the design review and helped design our slide deck. I also incorporated the feedback from the presentations and solidified my architecture for the text sentiment analysis. No matter which model and word vectorize I use, the general layout of the text analysis module is the same. Our team still needs to hash out how we will combine the results of the facial and textual emotion analysis. Our best bet right now is to create a composite score by combining the probabilities from both analyses and figuring out with emotion is the most probable.
Going forward, I’m going to do learn more about LSTM-CNNs as this model is something that I haven’t used before. I’m hoping to have the framework for the model done so that I can start training when I get back from Spring Break. Our Raspberry PI 4 has also been delivered. So if time allows, we can start setting it up see how the models perform on this weaker hardware.
0 Comments