flexible-yolov5
Bobo-y

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
- support nvidia tensor-core 4:2 sparsity.
- support QAT, for qat onnx export, need torch >=1.13(I only test on this version) 2023-10-17



