How long for training

[ShenZheng2000]

Hello, authors! I have a doubt about how long it takes to converge your model. Your manuscript mentions that "The proposed MBLLEN can be quickly converged after being trained for 5000 mini-batches". However, your train.py sets 200 epochs with 200 batches for each epoch. Therefore, the total mini-batches should be 40,000 instead of 5,000. Hope you can clarify it. Thanks!

[yjg123456]

是的 我感觉这里作者没有讲清楚

[Sherlock-hh]

hello did u solve the problem? I wonder if I change the batchsize 16 to 8, and step_epoch 200 to 400 ,because my gpu memory is not enough, dose it have influence to final results?

你好你好，我想问问您这边对batchsize这一块搞明白了，我现在在把batch_size 从16改成8了，step_epochs从200改成400了，因为gpu内存不够，这会对结果有影响吗，因为我的loss一直在1.2左右晃，感觉有点不对劲啊