Open fcod1998 opened 1 year ago
This means ur torch env is cpu-only. U should build a gpu torch version.
thanks a lot,i have solved it
------------------ 原始邮件 ------------------ 发件人: "hlsheng1/RDIoU" @.>; 发送时间: 2022年11月1日(星期二) 下午3:41 @.>; 抄送: " @.**@.>; 主题: Re: [hlsheng1/RDIoU] excuse me,what this question mean? (Issue #11)
This means ur torch env is cpu-only. U should build a gpu torch version.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
I'm also having the same issue, but didn't find any solution, can you give me some hint? Thanks a lot !
I found out what the problem was. Refer to https://github.com/traveller59/spconv, my previous spconv version was not correct, I should install spconv cuda version.
Hi,I was matching the spconv version to cuda to solve this problem.If that doesn't work, you can try different permutations of versions
I was matching the spconv version to cuda to solve this problem.
@.***
------------------ 原始邮件 ------------------ 发件人: "hlsheng1/RDIoU" @.>; 发送时间: 2022年12月18日(星期天) 上午9:17 @.>; 抄送: " @.**@.>; 主题: Re: [hlsheng1/RDIoU] excuse me,what this question mean? (Issue #11)
I'm also having the same issue, but didn't find any solution, can you give me some hint?
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
2022-10-29 11:08:56,145 INFO **Start training kitti_models/rdiou(default)1111** epochs: 0%| | 0/100 [00:00<?, ?it/s[Exception|native_pair]indices=torch.Size([64000, 4]),bs=4,ss=[41, 1600, 1408],algo=ConvAlgo.Native,ksize=[3, 3, 3],stride=[1, 1, 1],padding=[1, 1, 1],dilation=[1, 1, 1],subm=True,transpose=False SPCONV_DEBUG_SAVE_PATH not found, you can specify SPCONV_DEBUG_SAVE_PATH as debug data save path to save debug data which can be attached in a issue. epochs: 0%| | 0/100 [00:01<?, ?it/s] Traceback (most recent call last): File "train.py", line 204, in
main()
File "train.py", line 159, in main
train_model(
File "/root/RDIoU-main/tools/train_utils/train_utils.py", line 86, in train_model
accumulated_iter = train_one_epoch(
File "/root/RDIoU-main/tools/train_utils/train_utils.py", line 38, in train_one_epoch
loss, tb_dict, disp_dict = model_func(model, batch)
File "/root/RDIoU-main/pcdet/models/init.py", line 30, in model_func
ret_dict, tb_dict, disp_dict = model(batch_dict)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, kwargs)
File "/root/RDIoU-main/pcdet/models/detectors/rdiou_net.py", line 11, in forward
batch_dict = cur_module(batch_dict)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, *kwargs)
File "/root/RDIoU-main/pcdet/models/backbones_3d/spconv_backbone.py", line 140, in forward
x = self.conv_input(input_sp_tensor)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(input, kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/spconv-2.2.3-py3.8-linux-x86_64.egg/spconv/pytorch/modules.py", line 137, in forward
input = module(input)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/spconv-2.2.3-py3.8-linux-x86_64.egg/spconv/pytorch/conv.py", line 383, in forward
raise e
File "/root/miniconda3/lib/python3.8/site-packages/spconv-2.2.3-py3.8-linux-x86_64.egg/spconv/pytorch/conv.py", line 370, in forward
outids, indice_pairs, indice_pair_num = ops.get_indice_pairs(
File "/root/miniconda3/lib/python3.8/site-packages/spconv-2.2.3-py3.8-linux-x86_64.egg/spconv/pytorch/ops.py", line 156, in get_indice_pairs
num_act_out = SpconvOps.get_indice_pairs(alloc,
RuntimeError: /io/build/temp.linux-x86_64-cpython-38/spconv/build/core_cc/src/csrc/sparse/all/SpconvOps/SpconvOps_get_indice_pairs.cc(65)
not implemented for CPU ONLY build.