LiuNull

Results 2 issues of LiuNull

I have noticed that you had a closed issue about best results in ModelNet40. You said before the changing, your results was only 0.X% accuracy gap with the paper. But...

想请问一下在300-w数据集上,stage1和stage2差不多要训练几个epoch呢。 另外训练好之后的误差在多少说明模型效果比较好呢?我目前只训练了stage1,batch_error在0.8左右一直下不去,在300W-test上做测试的时候mean_error在0.07。 最好还想请问一下原代码中的validationSet是不是有问题,和trainSet的数据重复了? 非常希望得到您的解答,谢谢。