Support Objects365 pretrain and Adding the DINO++ model can achieve an accuracy of 63.4mAP at a model scale of 200M(Under the same scale, the accuracy is the best)
* complete yolox introduction
* fix env problem with nni2.6.1
* fix yolox-edge problem
* add docker turtorial
* add blade test
* support old export yolox model
Co-authored-by: wuziheng <zhoulou.wzh@alibaba-inc.com>
* add attention layer and more loss function
* add attention layer and various loss functions
* add siou loss
* add tah,various attention layers, and different loss functions
* add asff sim, gsconv
* blade utils fit faster
* blade optimize for yolox static & fp16
* decode output for yolox control by cfg
* add reparameterize_models for export
* e2e trt_nms plugin export support and numeric test
* split preprocess from end2end+blade, speedup from 17ms->7.2ms
Co-authored-by: zouxinyi0625 <zouxinyi.zxy@alibaba-inc.com>