TensorFlow.js in the browser: why one new tensor shape cost 8-17 seconds, and how I cut a 40 s freeze
I run a photo enhancer that does super-resolution fully in the browser: TensorFlow.js on WebGL, nothing is uploaded. The first version used the upscaler library (UpscalerJS). On a 1.2 megapixel photo it took 60-110 seconds and froze the page for about 40 seconds. A user told me "it does not accept…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-09-30 22:17 · DEV Community — Machine Learning
TensorFlow.js in the browser: why one new tensor shape cost 8-17 seconds, and how I cut a 40 s freeze