Even
> I have trained on EBB dataset with Pytorch PyNET. Details: Training on level2, psnr on valid set(sampled some pic from ebb) can reach ~23. But on level1, psnr on...
@csdwren So, this method is not applicable in industry applications right?
> The baseline for which dataset? For the stereo dataset
@tkone2018 Poor performance.
Sorry for the loss of detailed instructions! Because i'm busy at work recently. I will give some detailed instructions when i'm free.
@TianyeAlex 没测过，可以输出比较一下
@lenalinyajing 已更新
@wait1988 图像名称就包含标注信息，不需要单独的标注文件
@huanhuanxuxu 图片名称包含所有的关键点坐标，请参考process_plate.py 和dataset中label的解析方式。
@ideaflow 请参考https://github.com/CaptainEven/RepNet-MDNet-VehicleReID