dakshjain-1616/Quantisation-Awareness-training-by-NEO

Quantization-Aware Training pipeline for MobileNetV2 in PyTorch, reaching around 9x model compression for edge deployment. Simulates INT8 during fine-tuning so the final quantized network keeps baseline accuracy.

2 best points · 2 comments · 1 Hacker News post · 9 GitHub stars · View on GitHub

Hacker News discussions

• 9x MobileNet V2 size reduction with Quantization aware training (2 points, 2 comments, by gauravvij137, 2026-02-16)