Menu

One Good Question Repriced TTA: Ten Views Now Cost 8%
πŸ“°

One Good Question Repriced TTA: Ten Views Now Cost 8%

DEV Community: pytorchΒ·b1ackjack12Β·7 days ago
#ClBRTtQJ
#devtopytorch#devto#dev#batch#sequential
Reading 0:00
15s threshold

The test-time augmentation post ended with a price list: +0.56 accuracy for 2.0x inference cost, +0.71 for 10.0x, measured cleanly and scaling exactly with view count. Then a sharp question about it came my way β€” one my benchmark had quietly dodged: those timings ran the flipped copies as a second forward pass β€” what happens if you concatenate them into the same batch? Does the overhead stay linear, or does something nonlinear happen when the batch doubles?

I measured two rows to answer the question, and the two rows demanded the full table, because they implied the original post's price list is only the worst-case menu . Here's the sweep: five batch sizes, the usual CIFAR ResNet18, warmed-up CUDA-event timings, median of up to 100 reps.…

Continue reading β€” create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.