MR-lander
MR-lander
> @monajalal , @zdm123 , @amirhfarzaneh, @yidan216home , I get the same problem with train my data , the rpn_box_loss is nan, after some research, it's because in the file...
> 怎么可能是验证集和训练集一样呢。。。。。。 > 参数什么的也要自己调的啊，我只是放上了我使用的默认的参数。多调多观察吧 博主你好，想问一下主要需要调哪些参数来提高map啊，谢谢
> > @LyuYifan > > thank you for the illustration, that was very helpful. > > Welcome. I have already solved the problem I mentioned. The code is right. I...
> > > > > > > > > > 同样的疑问，我感觉是分割背景，肝脏组织和癌灶三部分的损失，不知道对不对，希望有同学可以解答一下？ > > > > > > > > > > 还有一个同样的混淆，测试分割效果很差不知道怎么改进 > > > > > > > >...
and if I use cpu , it will be killed
你遇见过test的时候爆显存的情况吗，用cpu模式进程也会被kill
Do you solve the problem?
> 您好，我也是图像超分的方向，不知道您做出用热力图做出结果了吗？我尝试用grad-cam作图，但结果远不如分类和检测的展示效果好。不知道您的损失函数放的是什么呢？ 您好，我目前也是用grad-cam做图像复原相关的grad-cam图，效果也是非常不好，请问你目前解决了吗
> > Did you solve the problem? > > I have the same problem here, very confused. > > when I use my own dataset as the test ,the dice=0...
> Thanks! I tried skipping the data processing,the training process is normal, loss is always falling, but the test is very unstable (sometimes dice = 0.2, sometimes dice = 0)....