IR-Net
IR-Net copied to clipboard
This project is the PyTorch implementation of our accepted CVPR 2020 paper : forward and backward information retention for accurate binary neural networks.
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,...
grad_input = k * t * (1 - torch.pow(torch.tanh(input * t), 2)) * grad_output Expected all tensors to be on the same device, but found at least two devices ,...
I have try in CIFAR-10 with VGG-small, and can get similar result as you mention in your paper. Your work is really useful. And I have trouble in deploying your...
Can you please provide a training file (trainer.py) for the imagenet dataset?thinks
Hello, sorry for similar question. You have mentioned you used bi-real net structure for fair competition. Is it a popular way to use bi-real net structure for quantization even for...
Can you give details of the training steps?
Hello, Thank you very much for sharing your work. When I trained ResNet18 for CIFAR10, it gives 86% accuracy on the validation data. I use the same hyperparameters of https://github.com/kuangliu/pytorch-cifar...