Open zyfsa opened 6 years ago
@zyfsa Hi, this paper has been accepted to CVPR2018. It spend around 4500 MB GPU memory to test KITTI. You may need a GPU with higher capacity if the code is out of memory
In the latest version of the code the crop size is 1232x368 for KITTI. Shouldn't it be 1248x384?
@thias15 We pad the width and height of images to the multiple of 32.
训练集和测试集图像尺寸不一样对测试结果影响大吗?例如SceneFlow数据集上图像都填充到544*960是不是性能更好?
sceneflow数据集的尺寸不是540 960吗,代码中是进行了裁剪,不是填充,怎么得到544 960的结果
hello,is this a cvpr2018 poster paper or arxiv paper? Besides, when you test, your input is not crop(256512), is 3841248. If it will be out of memory? if my code will be out of memory when 384*1248, how can I test? thank you very much.