Results
3
issues of
夏青
执行: python prepare_data/gen_hard_example.py --test_mode=R_Net 会先把PNet先跑一遍,这个很耗费时间,请问正常吗?
Q群已经满员了
2
求加
when I train this recognition model , the valid result always is 0.5 ,and the total loss change from 40 to 8. can you explain the results?