ResNet 50 论文

摘要

ResNet 50 is a crucial network for you to understand. It is the basis of much academic research in this field. Many different papers will compare their results to a ResNet 50 baseline, and it is valuable as a reference point. As well, we can easily download the weights for ResNet 50 networks that have been trained on the Imagenet dataset and modify the last layers (called **retraining** or **transfer learning**) to quickly produce models to tackle new problems. For most problems, this is the best approach to get started with, rather than trying to invent new networks or techniques. Building a custom dataset and scaling it up with data augmentation techniques will get you a lot further than trying to build a new architecture.