ouguozhen

@H-xie 兄弟,你是怎么构建训练集的呢?只是运行一遍font2img.py 和pacage.py是不行的吧?假如说我想训练关于A,B,C,D四种字体的模型,那么我应该怎么去构建训练集呢?

@SHUSHENGQIGUI could you tell me what's your input of the experiment?

@SHUSHENGQIGUI Thank you for your reply! however, is it not that each input image can only contain two characters?

@Dawson-huang do you solve this problem? i meet the same

> Can you provide some suggestions on how to install the required GPU version correctly? I am having trouble install it. I am trying to install it inside a gpu...

你好，对训练有点疑问，在训练的时候，每一个batch_size是只训练一种任务吗，比如分类或者box_reg，或者landmark。还是说每个batch_size里面，这几个任务都包含了，然后里面的数据分布是按照一定的比例来的。