EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Model Scaling: (a) is a baseline network example; (b)-(d) are conventional scaling that only increases one dimension of network width, depth, or resolution. (e) is our proposed compound scaling method that uniformly scales all three dimensions with a fixed ratio.
EfficientNet: Increasing the Accuracy and Robustness CNNs Transfer Learning for EfficientNet was performed on the CIFAR10 dataset in the application prepared as an attachment to the blog post.
🍫 References: