shenglunch
shenglunch
在阅读时这部分的内容一直不通顺，在跟着您的逻辑推导时觉得13.9公式表达有问题，而且13.8是不是应该是一种近似而不是精确成立的？
Very nice job! Could you provide the code to get absolute depth values in meters, and camera parameters to generate the pointcloud? Thanks!
Very nice job! I try to fine-tune your pretrained model with multiple GPUs？But the code ‘layer_1_rn = self.scratch.layer1_rn(layer_1)’ yields an error. RuntimeError: Expected all tensors to be on the same...
Very nice job! Could you provide the code to get absolute depth values in meters, and camera parameters to generate the pointcloud? Thanks!
贺博您好，我试着使用欧拉法，中值积分和龙格库塔法（msckf-vio）进行计算，发现使用龙格库塔法没能提升精度，这不符合我之前了解的一些结论，请问是怎么回事？ 下图是不同方法的误差，计算方法是err=gt位移-计算位移，再计算err的二范数。请问这种计算方式合适么？ mid是中值积分，runge是龙格库塔，rungem是将龙格库塔法中角速度替换为中值，euler是欧拉法。 
Very nice job and dataset ! But, how to get absolute depth values from depth_zbuffer in meters? Thx!
How to set your model to detect pedestrian and cyclist?