alsilence
alsilence
how can i not use pre-models to train my images ?bacause i want to know the difference between use pre-models(like vgg16) or not
Thanks for your great work.I want to train the network, how many gpus did you use when training?
您好，因为电脑内存不足的原因没有使用您的pre-possessed DTU，使用了 MVS的DTU数据集进行了训练，默认参数没有修改，但现在自己训练的模型效果很不理想，fusion之后没有生成点云，有可能是什么原因呢。望回复，感谢。
Hi,thanks for your work! I got some problem when running setup.py install, can you share your version of pytorch ,cuda and cudnn .I think may be mine is not suitable.Thanks!
请问这个project是只能用cpu跑吗，cpu跑的话一帧要画0.5s，有什么方法可以改成gpu版本的吗