SpatioTemporalSegmentation
SpatioTemporalSegmentation copied to clipboard
chrischoy
4D Spatio-Temporal Semantic Segmentation on a 3D video (a sequence of 3D scans)
Hello, Thanks for your codes, I find the MinkowskiEngine 0.5 is released. So, Would you consider updating the code to the latest version？ thanks, zihui
Do you have any models only trained on the training set (without validation set)? I cannot reproduce your result due to the lack of hardware, but I want to test...
Hi, Chrischoy. Thanks for your excellent work, and I benefit greatly from your work. I noticed that RandDropout has an unused parameter called **dropout_application_ratio**. I presumed it should control whether...
When I ran the scannet demo of this project,it said : Traceback (most recent call last): File "/home/iipl/SpatioTemporalSegmentation/demo/scannet.py", line 127, in model = Res16UNet34C(3, 20, config).to(device) File "/home/iipl/SpatioTemporalSegmentation/models/res16unet.py", line 23,...
Hello,I used to train this network with my own datasets. But I found a problem.the version of the MinkowskiEngine Project is higher than this train network, which means , the...
When i use these code to train this network with multi GPU: if torch.cuda.device_count() > 1: model = torch.nn.DataParallel(model) model = model.cuda() It send me this error： RuntimeError: Caught RuntimeError...
I encountered this issue after modified the S3DIS training code to multi GPU: File "/home/zfeng/.conda/envs/mink/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in __call__ result = self.forward(*input, **kwargs) File "/home/zfeng/.conda/envs/mink/lib/python3.7/site-packages/torch/nn/modules/batchnorm.py", line 107, in forward exponential_average_factor,...
I encountered this problem when trying to run ``` ./scripts/train_stanford.sh 4 "default" "--stanford3d_path ./Stanford3D" ``` When I set --num_workers to 0，it reports as follows: ``` ./scripts/train_stanford.sh: line 34: 30654 Segmentation...
anyone could tell me difference of these ConvType? i.e. ME.RegionType.HYPERCUBE,..., if i want to build a Spatio Module, which ConvType should i use? i dont know why these are two...
@chrischoy @panyunyi97 @fengziyue thanks for open sourcing the wonderfull work , i had few queries Q1 have you trained the architecture on the available other dataset like semanttic Kitti and...
