pawopawo
pawopawo
Thank you very much for your reply, I will try it out and give feedback in time
> 主要是参考vgg16ssd增加了mobilenetv1ssd，能运行训练但meanAP不到0.01。 你的mobilenet是错误的，貌似漏了BN层。
The `shard_id` is not found in the `fn.external_source function`
Sorry, I don’t understand too much. Can you help implement this part of the code? Thank you very much~
谢谢～请问蒸馏训练都是使用soft label以及JS div loss吗？没有使用ground truth？
如果一张图片同时属于多个label时该怎么办呢？每个label都加入这张图片吗？
Thank you for your reply, Do different blocks (shufflenet or ResNeSt) and different FLOPs require manual adjustment of the range of these [hyper-parameters](https://github.com/zhanghang1989/RegNet-Search-PyTorch/blob/10bb5967eb5a34521f52c270a7c195f348295b25/arch/regnet.py#L133)?