11. Transfer Learning for Domain-Specific Image Classification with Small Datasets

Transfer learning lets you take a small dataset and produce an accurate model. This method uses large networks that were trained for a long time on huge datasets, transferring that knowledge into our own network. Follow along with Lukas using the Python scripts here: https://github.com/lukas/ml-class/tree/master/videos/transfer-learning This is part of a long, free series of tutorials teaching engineers to do deep learning. Leave questions below, and check out more of our class videos: Class Videos: http://wandb.com/classes Weights & Biases: http://wandb.com