In this project, we have implemented a model to recognize real-time facial emotions given the camera images. Current approaches would read all data and input it into their model, which has high space complexity. Our model is based on the Convolutional Neural Network utilizing the PyTorch library. We believe our implementation will significantly improve the space complexity and provide a useful contribution to facial emotion recognition. Our motivation is to understanding clearly about deep learning, particularly in CNNs, and analysis real-life scenarios. Therefore, we tunned the hyper parameter of model such as learning rate, batch size, and number of epochs to meet our needs. In addition, we also used techniques to optimize the networks, such as activation function, dropout and max pooling. Finally, we analyzed the result from two optimizer to observe the relationship between number of epochs and accuracy.

翻译：本项目实现了一种基于摄像头图像进行实时面部表情识别的模型。现有方法需将全部数据输入模型，导致空间复杂度过高。本模型采用基于PyTorch框架的卷积神经网络（CNN），我们认为该实现能显著降低空间复杂度，为面部表情识别领域做出有益贡献。研究动机在于深入理解深度学习（特别是CNN）机制，并分析实际应用场景。为此，我们针对学习率、批处理大小及训练轮数等超参数进行了调优。此外，还采用了激活函数、随机失活（dropout）及最大池化等技术优化网络结构。最后通过对比两种优化器的实验结果，分析了训练轮数与准确率之间的关联性。