Duo Li

involution. [CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator

mobilenetv2.pytorch. 72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

mobilenetv3.pytorch. 74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

efficientnetv2.pytorch. PyTorch implementation of EfficientNetV2 family

octconv.pytorch. PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

PSConv. [ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer

face-attribute-prediction. Face Attribute Prediction on CelebA benchmark with PyTorch Implementation

HBONet. [ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions, surpassing MobileNetV2

ghostnet.pytorch. 73.6% GhostNet 1.0x pre-trained model on ImageNet

DHM. [CVPR 2020] Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives

regnet.pytorch. PyTorch-style and human-readable RegNet with a spectrum of pre-trained models

dgconv.pytorch. PyTorch implementation of Dynamic Grouping Convolution and Groupable ConvNet with pre-trained G-ResNeXt models

mobilenetv4.pytorch. PyTorch implementation of MobileNetV4 family

lambda.pytorch. PyTorch implementation of Lambda Network and pretrained Lambda-ResNet

SAN. [ECCV 2020] Scale Adaptive Network: Learning to Learn Parameterized Classification Networks for Scalable Input Images

condconv.pytorch. PyTorch implementation of CondConv and MobileNetV2 model

mlp-mixer.pytorch. PyTorch implementation of MLP-Mixer

dot-product-attention. A collection of self-attention modules and pre-trained backbones

mobilenext.pytorch. Rethinking Bottleneck Structure for Efficient Mobile Network Design

efficientnet-lite.pytorch. PyTorch implementation of EfficientNet-lite and a spectrum of pre-trained models on ImageNet

deeplearning.ai-CNN. Implementation of course Convolutional Neural Networks created by deeplearning.ai on Coursera

ssd.pytorch. A PyTorch Implementation of Single Shot MultiBox Detector

attention-transfer. Improving Convolutional Networks via Attention Transfer (ICLR 2017)