SimIPU
SimIPU copied to clipboard
zhyever
[AAAI 2021] Official Implementation of "SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations"
Hello author, in the SimIPU paper, I find that the inter-modal module loss is gradient truncation in the point cloud features. When gradient backpropagation is considered, this step does not...
# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...
[Question] Is this paper aims at pretraining a better camera backbone? Actually, when I take a look at the given pth., it seems it is the pretrained parameter of a...
Hi, thanks for sharing your great work. I encounter some issues during creating data by running create_data.py First create reduced point cloud for training set [ ] 0/3712, elapsed: 0s,...
您好，首先，感谢您出色的工作！我在复现moca时，发现moca_r50_kitti.py中的一些预训练模型没有看到，请问您公开这些模型了吗？我可以从哪得到呢？另外，您在复现moca时是否使用了提出的数据增强方法呢？因为我看您的模型中的一些代码没有按照moca的修改（https://github.com/open-mmlab/mmdetection3d/pull/327/commits/a02698d01975908fb2b95d8dfea826c3824f3a6f），比如：point_fusion.py。 还有moca_r50_kitti.py中的blending_type=['box', 'gaussian', 'poisson'] 改成了 blending_type=None貌似就没有img patch粘贴了。 # load_from = 'checkpoints/densecl_r50_coco_1600ep_convert.pth' # densecl # load_from = 'checkpoints/densecl_r50_imagenet_200ep_convert.pth' # densecl # load_from = 'nfs/lzy/cross_intro_moco_pointCenterRotate/pretrain_fix_moco_bugs/epoch_50.pth' # best # load_from = 'nfs/lzy/waymoExps/pretrain_fix_moco_bugs/epoch_20.pth' #...
