Tan

> > I'm looking at this, and will probably roll my own at some point. > > I guess I'm just curious if the authors answer what the "count" parameter...

> Hi, can you share the script to generate` 'latency_table@XXX/YYY_lookup_table.yaml'`？I want to know the details. do you have the latency model predictor details ? How to build this model?

> Thanks for great work! This code uses a pytorch model but you mention that the models are deployed on mobile in tf-lite, do you convert a pytorch model with...

> As far as I can tell, the folders are the different stages of the _progressive shrinking_ algorithm, `kernel2kernel_depth` is the training step from elastic kernel to elastic kernel and...

> Dear @han-cai , > > Thanks for sharing your excellent work. I am just curious about how we can apply this technique to detection problem (training on the COCO...

supernet的训练应该是直接设置成最大去训练吧，加载了作者给的模型可以finetune到自己的数据上

> Hey, thanks for your amazing work! > > can you share the Latency Estimator and the evolutionary search code based on the neural-network-twins to get a specialized sub-network? >...

> Hi, > > Congratulations on this great job. I was amazed by your solution in CVPR2020 competition. > > Is there any tutorial to use this work on a...

> Thanks for your appreciation, our paper is under review and will be officially released around October. Code will be released after that. I cannot wait to seeing the code!...

> ok Hi @yxchng 遇到了与你一样的问题： CustomOperator::Get()->Find(params.op_type) != nullptr Cannot find custom operator negativemining_onlylandmark 想请教一下这个问题你怎么解决的？