There are 0 repository under dcnv2 topic.
More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam,dcn and so on), and tensorrt
DCNv2 supports decent pytorch such as torch 1.5+ (now 1.8+)
练习下用pytorch来复现下经典的推荐系统模型, 如MF, FM, DeepConn, MMOE, PLE, DeepFM, NFM, DCN, AFM, AutoInt, ONN, FiBiNET, DCN-v2, AFN, DCAP等
Don't feel pain to use Deformable Convolution
NN-based radar-camera post sensor fusion implemented by TensorRT
Useful plugins for Pytorch1.5+ and TensorRT7/8.
[Pattern Recognition]Video Saliency Prediction using Enhanced Spatiotemporal Alignment Network
A fully cuda implementation of DCNv2(deformable convolution) forward. Without dependent of cuTorch(THC).
CenterNet Fixed For Google Colab
ncnn impl of ppyolov2 and ppyolo and ppyoloe.
This is a real time instance segmentation task implemented with YOLACT++ and DCNv2 on Google Colab.
PyTorch Deformable Convolutional Networks v2 (no compile required)