search

zhiqiangdon / CU-Net

Code for "Quantized Densely Connected U-Nets for Efficient Landmark Localization" (ECCV 2018) and "CU-Net: Coupled U-Nets" (BMVC 2018 oral)
Apache License 2.0
227 stars 40 forks source link

Train Val split #8

Open jingyang2017 opened 5 years ago

jingyang2017 commented 5 years ago

Thanks for making the code available! Could you explain how you split the data in MPII's "annot"? Based on the provided code, the training image number is 25925 and the validation image number is 2958 Is this data split universally agreed or just for this paper? Because I found in https://github.com/leoxiaobin/deep-high-resolution-net.pytorch/issues/34 The Training and Validation split is different. Thanks