search

htqin / IR-Net

[CVPR 2020] This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.
177 stars 38 forks source link

Infference speed #20

Open imsotable opened 2 years ago

imsotable commented 2 years ago

hello，thank you for your excellent work! I still have a question,does the high inference speed of BNN also need to be deployed on the high-performance inference framework ,such as dabnn, otherwise the inference speed will not be much different from the original?

kgp123123 commented 1 year ago

Can you reproduce the results on Small-VGG? I tried using the provided code but only managed to achieve around 88% accuracy even in full precision.

kgp123123 commented 1 year ago

all-VGG? I tried using the provided code but o

Epoch is 300, batch is 128, lr is 0.007