Understanding num_workers
Why DataLoader num_workers matters: processes hide load latency behind GPU work, how to find the sweet spot, and the memory/GIL pitfalls that come with the pool.
Related
9 min read · intermediate
Clear explanations of core machine learning concepts, from foundational ideas to advanced techniques. Understand attention mechanisms, transformers, skip connections, and more.
Why DataLoader num_workers matters: processes hide load latency behind GPU work, how to find the sweet spot, and the memory/GIL pitfalls that come with the pool.
9 min read · intermediate
Master sequential vs strided memory access patterns. Learn how cache efficiency and hardware prefetching affect application performance.
8 min read · intermediate
Trace a target query through source keys, attention weights, and a weighted value mix. Understand cross-attention origins, shapes, masks, and applications.
7 min read · intermediate
Compare nearest-neighbor and bilinear image resizing, see aliasing when downsampling, and understand aspect ratio, letterboxing and mask interpolation.
4 min read · beginner
Explore VAE latent space in deep learning. Learn variational autoencoder encoding, decoding, interpolation, and the reparameterization trick.
5 min read
Explore ColBERT and other multi-vector retrieval models that use fine-grained token-level matching for superior search quality.
12 min read · advanced