Open wangjiangyuan opened 2 years ago
Hi @wangjiangyuan once you generate the candidates tsv files in train mode, you can use part of that for train and part for validation purpose. You can also run the preprocess separately for train and validation on different regions.
Hi, I got the truth_vcf . I want to train the data using the truth vcf by 5-fold-cross-validation analysis, and I got the dataset that including many files by 'process.py'. However I don't know how to get the vaildation tsv. Could you help me? Thanks, Jiangyuan