Blog
Self-published2021Sometimes the useful signal sits in a hidden layer rather than the output. We compare three ways to read those activations in PyTorch, from forward hooks to slicing the module list, and use them to pull out embeddings.
Self-published2021We compute channel-wise mean and standard deviation across an image dataset for normalization. The implementation batches through the data in PyTorch, so it never holds the full dataset in memory.
Self-published2020When labeled training data is scarce but unlabeled test data is plentiful, the test set is still useful. We pre-train on surrogate labels derived from it, then fine-tune on the real labels to lift network performance.
Self-published2020A convolutional network that grades diabetic retinopathy severity from retina photographs, built for a Kaggle competition and the Udacity ML Engineer program. We cover retina-specific preprocessing, augmentation, and the ordinal grading setup.