search

etrommer / torch-approx

GPU-accelerated Neural Network layers using Approximate Multiplications for PyTorch
https://etrommer.de/torch-approx
MIT License
7 stars 3 forks source link

Accuracy Benchmarking #11

Open etrommer opened 1 year ago

etrommer commented 1 year ago

Benchmarking of model accuracy when retrained using several modes is required.

Likely candidates for comparison:

etrommer commented 1 year ago

Corresponding issue in agn-approx repository

https://github.com/etrommer/agn-approx/issues/3

agn-approx is used to host high-level implementations of datamodules, network models, experiments, etc.