Waste Classification Using EfficientNet-B0

Waste management has become one of the emerging problems. A way to speed up the whole process is by doing waste sorting, which could be done by computer using image recognition. EfficientNet-B0 could be utilized in this scenario due to the more efficient architecture and comparable performance with others deep convolutional neural network. For this experimentation, we did transfer learning and fine-tuning on it, and then do hyperparameter exploration. We also did the same process on few other models, and EfficientNet-B0 achieves the best accuracy at 96% accuracy on training with one of the smallest models. While we got 91% accuracy on validation, we also discover that our model has noticeable difficulty in classifying recyclables waste.