Changlin Li
Changlin Li
@yanjishuang learning rate用的多少？你开了warm startup了么
Why do you want to do this? A sparse input can already be considered as a negative sample. And this repo , emmmm, does not support this. Still you can...
@tommyz94 what's the meaning of extract feature? Get weights of layer?
@tommyz94 Yes it is possible, you can hook out weights of layer and save it, from you checkpoint
> The official [PSMNet](https://github.com/JiaRenChang/PSMNet) was already ported to Python 3. So you should be able to compute disparity map already. What pseudo-lidar does is simply converting the disparity into depth...
@vvcatstar I run into same issue. Do you find any solution?
I carefully check the source code. This is due to torchsparse package. Under current setup, neuralrecon with torchsparse dependency can only work on cuda 10.2 and 11.1 or cpu mode.
> you can use code below to create .cam file in images direction in directions created from ARKIT. [https://blog.csdn.net/yxh505613923/article/details/124848887](url) Hi @PolarisYxh , I would if the same process applied to...
> Hi @JyotiLuxolis, I guess the pose matrix maybe is not perfect, so the texture of white table may be add to its nearby. I don't have a solution yet....
> clip_len (int): Determines how many frames are there in each clip. Defaults to 16. But when I open the folder of the preprocessed video I see more than 16...