awesome_lightweight_networks icon indicating copy to clipboard operation
awesome_lightweight_networks copied to clipboard

The implementation of various lightweight networks by using PyTorch. such as:MobileNetV2,MobileNeXt,GhostNet,ParNet,MobileViT、AdderNet,ShuffleNetV1-V2,LCNet,ConvNeXt,etc. ⭐⭐⭐⭐⭐

Results 6 awesome_lightweight_networks issues
Sort by recently updated
recently updated
newest added

use the pip install, will lose some package. look forward to fix it

很高兴看到轻量级网络的github工具包,我是SCNU大学的研究生,也在研究轻量级网络设计及剪枝这块,目前在写论文,论文完成后,可贡献源码到这个工具包中。

Could I train all the models easily like this ? https://rwightman.github.io/pytorch-image-models/training_hparam_examples/

您好,我想知道这个包是否还会更新? 我最近看到了一些新的网络,比如MobileViT v2,Parc-Net,EdgeNeXt等 请问您是否有计划在包内补充这些网络?

import torch from light_cnns import mobilevit_s model = mobilevit_s() model.eval() print(model) input = torch.randn(1, 3, 224, 224) y = model(input) print(y.size()) 这段代码输入报错:einops.EinopsError: Error while processing rearrange-reduction pattern "b d (h...

在工程实践的时候发现很多轻量模型的推理速度确实快,但是其所占的显存也很大,如mobileNetV3在显存中达到3到4G,这是正常的吗?因为其参数量其实很小,但是在显存中占据如此大的资源? 谢谢您的整合与工作